{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/multi-agent-actor-critic-for-mixed","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","arxiv_id":"1706.02275","date":"2017-06-07","proceeding":"NeurIPS 2017 12","authors":["Ryan Lowe","Yi Wu","Aviv Tamar","Jean Harb","Pieter Abbeel","Igor Mordatch"],"abstract":"We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows. We then present an adaptation of actor-critic methods that considers action policies of other agents and is able to successfully learn policies that require complex multi-agent coordination. Additionally, we introduce a training regimen utilizing an ensemble of policies for each agent that leads to more robust multi-agent policies. We show the strength of our approach compared to existing methods in cooperative as well as competitive scenarios, where agent populations are able to discover various physical and informational coordination strategies.","url_abs":"https://arxiv.org/abs/1706.02275v4","url_pdf":"https://arxiv.org/pdf/1706.02275v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/openai/multiagent-particle-envs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/Abdelhamid-bouzid/Multi-Agent-Deep-Deterministic-Policy-Gradient","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/Ah31/maddpg_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/AleXander-Tsui/MPE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/Chan1998/MAAC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/EyaRhouma/collaboration-competition-MADDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/JinTanda/MADDPG_env","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/JohannesAck/MATD3implementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/JohannesAck/tf2multiagentrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/LXYYY/multiagent-particle-envs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/MrDaubinet/collaboration-and-competition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/NeuroCSUT/intentions","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/RL-WFU/multi_agent_attack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/SihongHo/multiagent-particle-envs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/SintolRTOS/multi-agent_Example","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/Steven-Ho/multiagent-particle-envs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/Stippler/cow-simulator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/Yutongamber/MADDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/Zorrorulz/MultiAgentDDPG-Tennis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/baicenxiao/shaping-advice","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/baoqianwang/iros22_darl1n","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/baradist/multiagent-particle-envs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/biemann/Collaboration-and-Competition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/biorobotics/PRD_environments","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/bonniesjli/MADDPG_Tennis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/bonniesjli/MADDPG_Tennis_UnityML","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/caslab-vt/SARNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/cyanrain7/trpo-in-marl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/cyanrain7/trust-region-policy-optimisation-in-multi-agent-reinforcement-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/cyoon1729/Multi-agent-reinforcement-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/darshil333/CSE574","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/debajit15kgp/multiagent-envs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/dtabas/multiagent-particle-envs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/facebookresearch/benchmarl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/gingkg/multiagent-particle-envs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/goldbattle/snakes_mal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/google/maddpg-replication","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/hepengli/multiagent-particle-envs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/isp1tze/MAProj","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/jansenkeith501/CS295-MADDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/jiayu-ch15/MPE-for-curriculum-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/jingdic/rgmcomm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/johannesharmse/multi_agent_RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/jyqhahah/rl_maddpg_matd3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/kargarisaac/macrpo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/karishnu/tf-agents-multi-particle-envs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/kishorkuttan/Multi-Agent-Deep-Deterministic-Policy-Gradient-actor-critic-deep-reinforcement-for-capacity-manageme","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/krasing/DRLearningCollaboration","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/ksajan/DDPG-MAPE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/lachisis/multiagent-particle-envs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/madhur-tandon/RL-Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/madras-simulator/Multi-Agent-Particle-Environment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/marwanihab/RL_Tag_Game","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/marwanihab/RL_Testing_Noise_ASRN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/mauricemager/multiagent-robot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/morning9393/HAPPO-HATRPO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/openai/maddpg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/pr-shukla/maddpg-keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/qi-pang/mdpfuzz","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/quantumiracle/mars","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/rainandwind1/MADDPG-reconstruct","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/rainandwind1/MERL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/rainandwind1/Maddpg_multiagent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/rallen10/multiagent-particle-envs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/raoshashank/Tennis-with-MADDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/schroederdewitt/multiagent-particle-envs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/semitable/multiagent-particle-envs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/shariqiqbal2810/maddpg-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/shariqiqbal2810/multiagent-particle-envs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/starry-sky6688/MADDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/thechrisyoon08/Multi-agent-reinforcement-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/thechrisyoon08/marl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/tkarr21/multagent-particle-envs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/tkarr21/multiagent-particle-envs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/wsjeon/multiagent-particle-envs-maac","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/wsjeon/multiagent-particle-envs-v2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/xuehy/pytorch-maddpg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/yannbouteiller/gym-airsimdroneracinglab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/zoeyuchao/MPE-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/zoeyuchao/MPEnew-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/zowiezhang/stas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"multi-agent-actor-critic-for-mixed","repo_url":"https://github.com/ray-project/ray/tree/master/rllib","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"multi-agent-reinforcement-learning","task_name":"Multi-agent Reinforcement Learning"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"smac-1","task_name":"SMAC+"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"maddpg","method_name":"MADDPG"},{"method_slug":"q-learning","method_name":"Q-Learning"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"maddpg","name":"MADDPG","full_name":"MADDPG"}],"results":[{"leaderboard":"/sota/smac-on-smac-def-armored-sequential","task":"SMAC+","dataset":"Def_Armored_sequential","model":"MADDPG","rank_in_archive_order":4,"of":11,"metrics":{"Median Win Rate":"90.6"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-def-infantry-sequential","task":"SMAC+","dataset":"Def_Infantry_sequential","model":"MADDPG","rank_in_archive_order":1,"of":11,"metrics":{"Median Win Rate":"100"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-def-outnumbered-sequential","task":"SMAC+","dataset":"Def_Outnumbered_sequential","model":"MADDPG","rank_in_archive_order":2,"of":11,"metrics":{"Median Win Rate":"81.3"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-off-complicated-sequential","task":"SMAC+","dataset":"Off_Complicated_sequential","model":"MADDPG","rank_in_archive_order":4,"of":4,"metrics":{"Median Win Rate":"0.0"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-off-distant-sequential","task":"SMAC+","dataset":"Off_Distant_sequential","model":"MADDPG","rank_in_archive_order":4,"of":4,"metrics":{"Median Win Rate":"0.0"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-off-hard-sequential","task":"SMAC+","dataset":"Off_Hard_sequential","model":"MADDPG","rank_in_archive_order":3,"of":4,"metrics":{"Median Win Rate":"0.0"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-off-near-sequential","task":"SMAC+","dataset":"Off_Near_sequential","model":"MADDPG","rank_in_archive_order":3,"of":4,"metrics":{"Median Win Rate":"75.0"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-off-superhard-sequential","task":"SMAC+","dataset":"Off_Superhard_sequential","model":"MADDPG","rank_in_archive_order":4,"of":4,"metrics":{"Median Win Rate":"0.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1706.02275","atlas_url":"https://app.syntology.ai/?focus=1706.02275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.02275"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1706.02275"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1706.02275"},"call":"get_harvested_code_for_paper(arxiv_id=\"1706.02275\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"1706.02275"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1706.02275\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1706.02275"},"call":"get_concepts_for_paper(arxiv_id=\"1706.02275\")"}],"by_repo":[{"repo":"openai/multiagent-particle-envs","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Abdelhamid-bouzid/Multi-Agent-Deep-Deterministic-Policy-Gradient","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"Ah31/maddpg_pytorch","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"AleXander-Tsui/MPE","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Chan1998/MAAC","kind":"listed","samples":11,"ran":5,"instrument":2,"unverified":6},{"repo":"EyaRhouma/collaboration-competition-MADDPG","kind":"listed","samples":5,"ran":2,"instrument":0,"unverified":3},{"repo":"JinTanda/MADDPG_env","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"JohannesAck/MATD3implementation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"JohannesAck/tf2multiagentrl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"LXYYY/multiagent-particle-envs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MrDaubinet/collaboration-and-competition","kind":"listed","samples":6,"ran":4,"instrument":0,"unverified":2},{"repo":"NeuroCSUT/intentions","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"RL-WFU/multi_agent_attack","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"SihongHo/multiagent-particle-envs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"SintolRTOS/multi-agent_Example","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Steven-Ho/multiagent-particle-envs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Stippler/cow-simulator","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Yutongamber/MADDPG","kind":"listed","samples":8,"ran":5,"instrument":4,"unverified":3},{"repo":"Zorrorulz/MultiAgentDDPG-Tennis","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","kind":"listed","samples":11,"ran":8,"instrument":0,"unverified":3},{"repo":"baicenxiao/shaping-advice","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2010.12718"],"harvested_for_calls":[{"arxiv_id":"2010.12718","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.12718"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.12718\")"}]},{"repo":"baoqianwang/iros22_darl1n","kind":"listed","samples":34,"ran":4,"instrument":1,"unverified":30},{"repo":"baradist/multiagent-particle-envs","kind":"listed","samples":5,"ran":4,"instrument":0,"unverified":1},{"repo":"biemann/Collaboration-and-Competition","kind":"listed","samples":4,"ran":4,"instrument":0,"unverified":0},{"repo":"biorobotics/PRD_environments","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"bonniesjli/MADDPG_Tennis","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"bonniesjli/MADDPG_Tennis_UnityML","kind":"listed","samples":5,"ran":3,"instrument":0,"unverified":2},{"repo":"caslab-vt/SARNet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"cyanrain7/trpo-in-marl","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"cyanrain7/trust-region-policy-optimisation-in-multi-agent-reinforcement-learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"cyoon1729/Multi-agent-reinforcement-learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"darshil333/CSE574","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"debajit15kgp/multiagent-envs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"dtabas/multiagent-particle-envs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"facebookresearch/benchmarl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2312.01472"],"harvested_for_calls":[{"arxiv_id":"2312.01472","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2312.01472"},"call":"get_harvested_code_for_paper(arxiv_id=\"2312.01472\")"}]},{"repo":"gingkg/multiagent-particle-envs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"goldbattle/snakes_mal","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"google/maddpg-replication","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"hepengli/multiagent-particle-envs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"isp1tze/MAProj","kind":"listed","samples":5,"ran":4,"instrument":0,"unverified":1},{"repo":"jansenkeith501/CS295-MADDPG","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jiayu-ch15/MPE-for-curriculum-learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jingdic/rgmcomm","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"johannesharmse/multi_agent_RL","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"jyqhahah/rl_maddpg_matd3","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"kargarisaac/macrpo","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"karishnu/tf-agents-multi-particle-envs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"kishorkuttan/Multi-Agent-Deep-Deterministic-Policy-Gradient-actor-critic-deep-reinforcement-for-capacity-manageme","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"krasing/DRLearningCollaboration","kind":"listed","samples":5,"ran":4,"instrument":0,"unverified":1},{"repo":"ksajan/DDPG-MAPE","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"lachisis/multiagent-particle-envs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"madhur-tandon/RL-Project","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1509.02971"],"harvested_for_calls":[{"arxiv_id":"1509.02971","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1509.02971"},"call":"get_harvested_code_for_paper(arxiv_id=\"1509.02971\")"}]},{"repo":"madras-simulator/Multi-Agent-Particle-Environment","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"marwanihab/RL_Tag_Game","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"marwanihab/RL_Testing_Noise_ASRN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"mauricemager/multiagent-robot","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"morning9393/HAPPO-HATRPO","kind":"listed","samples":3,"ran":3,"instrument":0,"unverified":0},{"repo":"openai/maddpg","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity","kind":"listed","samples":5,"ran":4,"instrument":0,"unverified":1},{"repo":"philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients","kind":"listed","samples":4,"ran":4,"instrument":0,"unverified":0},{"repo":"pr-shukla/maddpg-keras","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"qi-pang/mdpfuzz","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"quantumiracle/mars","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2207.08894"],"harvested_for_calls":[{"arxiv_id":"2207.08894","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2207.08894"},"call":"get_harvested_code_for_paper(arxiv_id=\"2207.08894\")"}]},{"repo":"rainandwind1/MADDPG-reconstruct","kind":"listed","samples":5,"ran":3,"instrument":0,"unverified":2},{"repo":"rainandwind1/MERL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"rainandwind1/Maddpg_multiagent","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"rallen10/multiagent-particle-envs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"raoshashank/Tennis-with-MADDPG","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"schroederdewitt/multiagent-particle-envs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"semitable/multiagent-particle-envs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2505.05262"],"harvested_for_calls":[{"arxiv_id":"2505.05262","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2505.05262"},"call":"get_harvested_code_for_paper(arxiv_id=\"2505.05262\")"}]},{"repo":"shariqiqbal2810/maddpg-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"shariqiqbal2810/multiagent-particle-envs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1509.02971"],"harvested_for_calls":[{"arxiv_id":"1509.02971","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1509.02971"},"call":"get_harvested_code_for_paper(arxiv_id=\"1509.02971\")"}]},{"repo":"starry-sky6688/MADDPG","kind":"listed","samples":3,"ran":2,"instrument":0,"unverified":1},{"repo":"thechrisyoon08/Multi-agent-reinforcement-learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"thechrisyoon08/marl","kind":"listed","samples":5,"ran":3,"instrument":0,"unverified":2},{"repo":"tkarr21/multagent-particle-envs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"tkarr21/multiagent-particle-envs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"wsjeon/multiagent-particle-envs-maac","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"wsjeon/multiagent-particle-envs-v2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"xuehy/pytorch-maddpg","kind":"listed","samples":3,"ran":3,"instrument":0,"unverified":0},{"repo":"yannbouteiller/gym-airsimdroneracinglab","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1911.04448"],"harvested_for_calls":[{"arxiv_id":"1911.04448","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1911.04448"},"call":"get_harvested_code_for_paper(arxiv_id=\"1911.04448\")"}]},{"repo":"zoeyuchao/MPE-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"zoeyuchao/MPEnew-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"zowiezhang/stas","kind":"listed","samples":4,"ran":4,"instrument":0,"unverified":0},{"repo":"ray-project/ray","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","assemblies":[{"assembly_sha256":"08dfe679226d8a4c","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The code implements a multi-agent actor-critic method with a centralized critic and decentralized actors, specifically the COMA (Counterfactual Multi-Agent) algorithm proposed in the paper.","centrality":"contribution","entry":"COMA","entry_sha256":"e6b6fc2b3a05ee48","n_bricks":4,"bricks":[{"entry":"COMA","code_sha256":"e6b6fc2b3a05ee48","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"d33580612fa8578d","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"6879c98b93ce7112","role":"model","order":2,"level":1,"status":"ran"},{"entry":"Memory","code_sha256":"51c877df80bace64","role":"helper","order":3,"level":1,"status":"ran"}],"ran_individually":4,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"1b8f52ac0b2e8498","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The paper claims this code implements a multi-agent actor-critic method where each agent has its own actor and critic networks to handle mixed cooperative-competitive environments.","centrality":"contribution","entry":"Actor","entry_sha256":"85e19366b66e12c8","n_bricks":1,"bricks":[{"entry":"Actor","code_sha256":"85e19366b66e12c8","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"1d5c41798982399a","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The code implements a multi-agent actor-critic algorithm where each agent has its own actor and critic networks, and the critic is provided with the observations and actions of all agents to address the non-stationarity of the environment.","centrality":"contribution","entry":"MADDPG","entry_sha256":"9bc56ac4d586a2d2","n_bricks":5,"bricks":[{"entry":"MADDPG","code_sha256":"9bc56ac4d586a2d2","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"DDPG","code_sha256":"a3a587bc7fe0ee77","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"394e91b566a8e7eb","role":"model","order":2,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"30449e98cba1cf61","role":"model","order":3,"level":1,"status":"ran"},{"entry":"Replaybuffer","code_sha256":"74c1bafecdee5848","role":"sampler","order":4,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"2d6cce03875d9bbb","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The paper claims this code implements a multi-agent actor-critic algorithm for mixed cooperative-competitive environments, where agents learn decentralized policies with centralized training using shared critic networks.","centrality":"contribution","entry":"MADDPG","entry_sha256":"6551e7add10520be","n_bricks":7,"bricks":[{"entry":"MADDPG","code_sha256":"6551e7add10520be","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Agent","code_sha256":"5d2d3b9ff319eb0d","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"ReplayBuffer","code_sha256":"ae26aa48075ee6cb","role":"sampler","order":2,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"147d57177bbffdd9","role":"model","order":3,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"6c1f59af0972c70e","role":"model","order":4,"level":1,"status":"ran"},{"entry":"OUNoise","code_sha256":"db3bd13d21d6150c","role":"helper","order":5,"level":1,"status":"ran"},{"entry":"hidden_init","code_sha256":"24ee38e114b38bce","role":"helper","order":6,"level":1,"status":"ran_honours"}],"ran_individually":5,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"2e507cae3bc95110","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The paper claims a Multi-Agent Actor-Critic method for mixed cooperative-competitive environments, where agents learn policies using decentralized actor-critic architectures with centralized training.","centrality":"contribution","entry":"Agent","entry_sha256":"f3e14c78a36f2168","n_bricks":5,"bricks":[{"entry":"Agent","code_sha256":"f3e14c78a36f2168","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ActorNetwork","code_sha256":"5d2b3c4f1fd1a9f4","role":"model","order":1,"level":1,"status":"ran"},{"entry":"CriticNetwork","code_sha256":"619856d2049bc612","role":"model","order":2,"level":1,"status":"ran"},{"entry":"OUActionNoise","code_sha256":"1ea60fdd30545832","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"c90519f77627be1f","role":"sampler","order":4,"level":1,"status":"ran"}],"ran_individually":4,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"47fc82edd0105864","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The code implements a multi-agent actor-critic method using a central attention critic to handle mixed cooperative-competitive environments.","centrality":"contribution","entry":"AttentionSAC","entry_sha256":"92865550d0fc369e","n_bricks":11,"bricks":[{"entry":"AttentionSAC","code_sha256":"92865550d0fc369e","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"AttentionAgent","code_sha256":"5e7a8abdf83466de","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"AttentionCritic","code_sha256":"23a16fcf13d93070","role":"model","order":2,"level":1,"status":"ran"},{"entry":"disable_gradients","code_sha256":"34bbc966346baa78","role":"helper","order":3,"level":0,"status":"unverified"},{"entry":"enable_gradients","code_sha256":"8e93ecfbcd3abb77","role":"helper","order":4,"level":0,"status":"unverified"},{"entry":"hard_update","code_sha256":"e6250f15677e1203","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"soft_update","code_sha256":"f36b207d39a0f07a","role":"helper","order":6,"level":0,"status":"unverified"},{"entry":"DiscretePolicy","code_sha256":"b4fe457a99be3144","role":"model","order":7,"level":1,"status":"ran"},{"entry":"BasePolicy","code_sha256":"e3579cc107de4c0a","role":"model","order":8,"level":1,"status":"ran"},{"entry":"categorical_sample","code_sha256":"8a12d52820205fa8","role":"helper","order":9,"level":1,"status":"ran_draft_wrong"},{"entry":"onehot_from_logits","code_sha256":"5290a0543b38c4dc","role":"helper","order":10,"level":1,"status":"ran_draft_wrong"}],"ran_individually":5,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":3,"ran_draft_wrong":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"4982b5225173dc2c","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The paper claims this code implements a multi-agent actor-critic method for mixed cooperative-competitive environments, where each agent's policy is trained using centralized critic information.","centrality":"contribution","entry":"MADDPG","entry_sha256":"a3dd086ac1fbb639","n_bricks":5,"bricks":[{"entry":"MADDPG","code_sha256":"a3dd086ac1fbb639","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"DDPGAgent","code_sha256":"bbf8b2fce98ed3c3","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"Network","code_sha256":"f6fceb14173df844","role":"model","order":2,"level":1,"status":"ran"},{"entry":"OUNoise","code_sha256":"555ae48ebffc59d4","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"hidden_init","code_sha256":"24ee38e114b38bce","role":"helper","order":4,"level":1,"status":"ran_honours"}],"ran_individually":5,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":4,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"50d65724740a3248","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The paper claims an implementation of a multi-agent actor-critic method for mixed cooperative-competitive environments, specifically the HAPPO (Heterogeneous-Agent Proximal Policy Optimization) algorithm.","centrality":"contribution","entry":"HAPPO","entry_sha256":"14f32d9aecd1c394","n_bricks":3,"bricks":[{"entry":"HAPPO","code_sha256":"14f32d9aecd1c394","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"PopArt","code_sha256":"cf971b9dc43b13b4","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"check","code_sha256":"9589eca5bae9de80","role":"helper","order":2,"level":1,"status":"ran_honours"}],"ran_individually":3,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"61e234a490fff2b4","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The paper proposes a multi-agent actor-critic algorithm where decentralized agents learn policies with centralized critics that use extra information about other agents' observations and actions during training.","centrality":"contribution","entry":"MADDPG","entry_sha256":"eb82e9aa0da99b86","n_bricks":3,"bricks":[{"entry":"MADDPG","code_sha256":"eb82e9aa0da99b86","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"b1b715fc5cea22be","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"601cec5195b4709d","role":"model","order":2,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"7e6cbb8b82abd9ee","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The code implements a multi-agent actor-critic method for mixed cooperative-competitive environments, where multiple agents learn policies using shared or individual critic networks to handle non-stationarity and variance in multi-agent settings.","centrality":"contribution","entry":"Agents","entry_sha256":"ce87b1d927fb04e1","n_bricks":6,"bricks":[{"entry":"Agents","code_sha256":"ce87b1d927fb04e1","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"ab8b87babe2b659e","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"9af882c88cb87dda","role":"model","order":2,"level":1,"status":"ran"},{"entry":"OUNoise","code_sha256":"a169b2555a871836","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"4cbc44a206f6120a","role":"sampler","order":4,"level":1,"status":"ran"},{"entry":"hidden_init","code_sha256":"24ee38e114b38bce","role":"helper","order":5,"level":1,"status":"ran_honours"}],"ran_individually":5,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"8062b0816299b3a2","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The paper proposes a multi-agent actor-critic method (MADDPG) for mixed cooperative-competitive environments, where each agent learns a centralized critic based on the observations and actions of all agents.","centrality":"contribution","entry":"Agent","entry_sha256":"a35198f4b2a98333","n_bricks":5,"bricks":[{"entry":"Agent","code_sha256":"a35198f4b2a98333","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"a17bd67f978b7355","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"6d943b1d04649de3","role":"model","order":2,"level":1,"status":"ran"},{"entry":"ExperienceBuffer","code_sha256":"b4481f38bbb906b5","role":"sampler","order":3,"level":1,"status":"ran"},{"entry":"OUActionNoise","code_sha256":"458174da77a0b0ce","role":"helper","order":4,"level":1,"status":"ran"}],"ran_individually":4,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"8d0ba20acebdbfcb","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The code implements a multi-agent actor-critic method where agents share a centralized critic and use policy optimization with trust region constraints to handle mixed cooperative-competitive environments.","centrality":"contribution","entry":"HAPPO_Policy","entry_sha256":"a78bf4c700ca5bb9","n_bricks":18,"bricks":[{"entry":"HAPPO_Policy","code_sha256":"a78bf4c700ca5bb9","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"fe0a30f4af252b51","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"Critic","code_sha256":"598a59b21df91031","role":"model","order":2,"level":0,"status":"unverified"},{"entry":"ACTLayer","code_sha256":"788933ff608baaea","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"CNNBase","code_sha256":"44f09ebd8f4371fa","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"MLPBase","code_sha256":"eb97113b662895e7","role":"helper","order":5,"level":1,"status":"ran"},{"entry":"RNNLayer","code_sha256":"ff5a06e4902f81ab","role":"helper","order":6,"level":1,"status":"ran"},{"entry":"check","code_sha256":"4829105008c71d83","role":"helper","order":7,"level":1,"status":"ran_honours"},{"entry":"init","code_sha256":"9de355e93051e4ad","role":"helper","order":8,"level":1,"status":"ran_draft_wrong"},{"entry":"Bernoulli","code_sha256":"ce4cd71349aedb12","role":"helper","order":9,"level":1,"status":"ran"},{"entry":"Categorical","code_sha256":"7e51bfa5785fa3e2","role":"helper","order":10,"level":1,"status":"ran"},{"entry":"DiagGaussian","code_sha256":"6072c4350e278037","role":"helper","order":11,"level":1,"status":"ran"},{"entry":"CNNLayer","code_sha256":"605e1876fb9959d1","role":"helper","order":12,"level":1,"status":"ran"},{"entry":"MLPLayer","code_sha256":"052cdd66a800bf26","role":"helper","order":13,"level":1,"status":"ran"},{"entry":"FixedBernoulli","code_sha256":"a48b952a1d356122","role":"helper","order":14,"level":1,"status":"ran"},{"entry":"FixedCategorical","code_sha256":"16be22c531bda7dd","role":"helper","order":15,"level":1,"status":"ran"},{"entry":"FixedNormal","code_sha256":"2430b3c71fa829d4","role":"helper","order":16,"level":1,"status":"ran"},{"entry":"Flatten","code_sha256":"dca1bdd65a0d90e0","role":"helper","order":17,"level":1,"status":"ran"}],"ran_individually":15,"ran_individually_constructed":12,"ran_individually_by_status":{"ran":13,"ran_draft_wrong":1,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"9c15b02245652b8a","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The code implements a multi-agent actor-critic method where each agent has its own actor and critic networks, and the critics are provided with the observations and actions of all agents to address non-stationarity in multi-agent environments.","centrality":"contribution","entry":"MADDPG","entry_sha256":"cc58450c6eb52f3a","n_bricks":5,"bricks":[{"entry":"MADDPG","code_sha256":"cc58450c6eb52f3a","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"cbd481c5cf284628","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"0d8d2fce5fa8c834","role":"model","order":2,"level":1,"status":"ran"},{"entry":"ReplayMemory","code_sha256":"14185602fbb4fa11","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"soft_update","code_sha256":"f0ba29ce2b116d79","role":"update_rule","order":4,"level":0,"status":"unverified"}],"ran_individually":4,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"a5801506ae9dbb86","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The code implements a multi-agent actor-critic algorithm (MADDPG) that addresses non-stationarity and high variance in multi-agent reinforcement learning by using centralized training with decentralized execution.","centrality":"contribution","entry":"MADDPG","entry_sha256":"bcbd9c4a35e9a9e0","n_bricks":5,"bricks":[{"entry":"MADDPG","code_sha256":"bcbd9c4a35e9a9e0","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"cbd481c5cf284628","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"a7f0fe3c4dffccc9","role":"model","order":2,"level":1,"status":"ran"},{"entry":"ReplayMemory","code_sha256":"535c542a4e41bb65","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"soft_update","code_sha256":"f0ba29ce2b116d79","role":"update_rule","order":4,"level":0,"status":"unverified"}],"ran_individually":4,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"acd0f0cb49555d04","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The paper proposes a multi-agent actor-critic method (MADDPG) for mixed cooperative-competitive environments, where agents learn decentralized policies with centralized training using shared critic networks.","centrality":"contribution","entry":"MADDPG","entry_sha256":"b38b019a971f0e14","n_bricks":7,"bricks":[{"entry":"MADDPG","code_sha256":"b38b019a971f0e14","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Agent","code_sha256":"c455aad4cf9e3d68","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"ReplayBuffer","code_sha256":"21d74b782714cf9e","role":"sampler","order":2,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"af7b2cc00bcf3971","role":"model","order":3,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"b89abb00e73f1560","role":"model","order":4,"level":1,"status":"ran"},{"entry":"OUNoise","code_sha256":"21303179927140a0","role":"helper","order":5,"level":1,"status":"ran"},{"entry":"hidden_init","code_sha256":"24ee38e114b38bce","role":"helper","order":6,"level":1,"status":"ran_honours"}],"ran_individually":5,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"b63df89ac823bf96","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The code implements a multi-agent actor-critic algorithm where each agent has its own actor and critic networks, and the critic is trained with centralized information from all agents to address non-stationarity in mixed cooperative-competitive environments.","centrality":"contribution","entry":"MADDPG","entry_sha256":"af4f065d2ca09a90","n_bricks":4,"bricks":[{"entry":"MADDPG","code_sha256":"af4f065d2ca09a90","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Agent","code_sha256":"6e3b52a2c0014b70","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"ActorNetwork","code_sha256":"19dd2e9c270f0dc6","role":"model","order":2,"level":1,"status":"ran"},{"entry":"CriticNetwork","code_sha256":"1a6507f0b27d66e3","role":"model","order":3,"level":1,"status":"ran"}],"ran_individually":4,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"cc6438be33b63b66","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The paper proposes a multi-agent actor-critic method (MADDPG) for mixed cooperative-competitive environments, and the DDPG class in the repository implements a core component of this method, specifically a deep deterministic policy gradient agent.","centrality":"contribution","entry":"DDPG","entry_sha256":"a4bedfc0dceee998","n_bricks":1,"bricks":[{"entry":"DDPG","code_sha256":"a4bedfc0dceee998","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"cd5c698f587b9e16","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The paper proposes a multi-agent actor-critic method called MADDPG for mixed cooperative-competitive environments, where each agent learns a centralized critic using information from all agents to address non-stationarity and variance issues in multi-agent reinforcement learning.","centrality":"contribution","entry":"MADDPG","entry_sha256":"6c6569c6b5d38959","n_bricks":4,"bricks":[{"entry":"MADDPG","code_sha256":"6c6569c6b5d38959","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Agent","code_sha256":"6e3b52a2c0014b70","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"ActorNetwork","code_sha256":"19dd2e9c270f0dc6","role":"model","order":2,"level":1,"status":"ran"},{"entry":"CriticNetwork","code_sha256":"1a6507f0b27d66e3","role":"model","order":3,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"cfb588886b6d696e","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The paper claims this code implements the Multi-Agent Actor-Critic algorithm for mixed cooperative-competitive environments.","centrality":"contribution","entry":"MADDPGAgentTrainer","entry_sha256":"b2f7329c7900cbee","n_bricks":34,"bricks":[{"entry":"MADDPGAgentTrainer","code_sha256":"b2f7329c7900cbee","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"AgentTrainer","code_sha256":"d0b7f852c271a2cb","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"BatchInput","code_sha256":"410b8121d522d60d","role":"helper","order":2,"level":0,"status":"unverified"},{"entry":"ReplayBuffer","code_sha256":"0ec668ec81ebce4d","role":"helper","order":3,"level":0,"status":"unverified"},{"entry":"p_train","code_sha256":"79a21c888d914a27","role":"model","order":4,"level":0,"status":"unverified"},{"entry":"q_train","code_sha256":"e03118d1752f94fe","role":"model","order":5,"level":0,"status":"unverified"},{"entry":"PlacholderTfInput","code_sha256":"bab2a198c923111d","role":"helper","order":6,"level":1,"status":"ran"},{"entry":"absolute_scope_name","code_sha256":"0f6bbf3f67ac6f9c","role":"helper","order":7,"level":0,"status":"unverified"},{"entry":"function","code_sha256":"5b6a9e8f5134b90d","role":"helper","order":8,"level":0,"status":"unverified"},{"entry":"make_pdtype","code_sha256":"731751ece9e0b766","role":"helper","order":9,"level":0,"status":"unverified"},{"entry":"make_update_exp","code_sha256":"0d1a79fa849ba189","role":"update_rule","order":10,"level":0,"status":"unverified"},{"entry":"minimize_and_clip","code_sha256":"51c9fbcd079c6fda","role":"helper","order":11,"level":1,"status":"ran"},{"entry":"scope_vars","code_sha256":"de2061bedccd8dc9","role":"helper","order":12,"level":0,"status":"unverified"},{"entry":"TfInput","code_sha256":"654b5868fdbabd66","role":"helper","order":13,"level":0,"status":"unverified"},{"entry":"scope_name","code_sha256":"706116fa3e5a5a6c","role":"helper","order":14,"level":0,"status":"unverified"},{"entry":"_Function","code_sha256":"8523867a9c545bdf","role":"helper","order":15,"level":0,"status":"unverified"},{"entry":"BernoulliPdType","code_sha256":"04989e6ce54eef99","role":"helper","order":16,"level":0,"status":"unverified"},{"entry":"DiagGaussianPdType","code_sha256":"9c5f519b1107c4a0","role":"helper","order":17,"level":0,"status":"unverified"},{"entry":"MultiDiscrete","code_sha256":"19525957eb332eb2","role":"helper","order":18,"level":0,"status":"unverified"},{"entry":"SoftCategoricalPdType","code_sha256":"9cf2b925ec95c7f2","role":"helper","order":19,"level":1,"status":"ran"},{"entry":"SoftMultiCategoricalPdType","code_sha256":"8371d56181f23309","role":"helper","order":20,"level":0,"status":"unverified"},{"entry":"var","code_sha256":"598184a2689d36d0","role":"helper","order":21,"level":0,"status":"unverified"},{"entry":"get_session","code_sha256":"61c6759fad1b2459","role":"helper","order":22,"level":0,"status":"unverified"},{"entry":"is_placeholder","code_sha256":"7e5ebeb6de3d3d4a","role":"helper","order":23,"level":0,"status":"unverified"},{"entry":"BernoulliPd","code_sha256":"7855bf32a05f6453","role":"helper","order":24,"level":0,"status":"unverified"},{"entry":"PdType","code_sha256":"a233d862ed1c5de8","role":"helper","order":25,"level":0,"status":"unverified"},{"entry":"DiagGaussianPd","code_sha256":"99ab37a0b854f64c","role":"helper","order":26,"level":0,"status":"unverified"},{"entry":"SoftCategoricalPd","code_sha256":"1fe728fdf693afaf","role":"helper","order":27,"level":0,"status":"unverified"},{"entry":"SoftMultiCategoricalPd","code_sha256":"9bb22eb75cfa28b6","role":"helper","order":28,"level":0,"status":"unverified"},{"entry":"sum","code_sha256":"fbab233112bf4d1e","role":"helper","order":29,"level":0,"status":"unverified"},{"entry":"mean","code_sha256":"8ebadf88476f8efe","role":"helper","order":30,"level":0,"status":"unverified"},{"entry":"Pd","code_sha256":"26b44f96043b4296","role":"helper","order":31,"level":0,"status":"unverified"},{"entry":"max","code_sha256":"cc0b8c4aa9b99165","role":"helper","order":32,"level":0,"status":"unverified"},{"entry":"softmax","code_sha256":"61d3f2ae09e0df23","role":"helper","order":33,"level":1,"status":"ran_fixture"}],"ran_individually":4,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":3,"ran_fixture":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"d2cdce2d3b6b4440","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The paper proposes a multi-agent actor-critic method where decentralized policies are trained with centralized critics that have access to all agents' observations and actions.","centrality":"contribution","entry":"MADDPG","entry_sha256":"05a2c85c2c068627","n_bricks":11,"bricks":[{"entry":"MADDPG","code_sha256":"05a2c85c2c068627","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"DDPGAgent","code_sha256":"23ccb70277ce98c1","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"average_gradients","code_sha256":"a3e542c9d6910a27","role":"helper","order":2,"level":0,"status":"unverified"},{"entry":"gumbel_softmax","code_sha256":"57d033c0c861f3d0","role":"helper","order":3,"level":1,"status":"ran_draft_wrong"},{"entry":"onehot_from_logits","code_sha256":"f925a8c266bb2532","role":"helper","order":4,"level":1,"status":"ran_draft_wrong"},{"entry":"soft_update","code_sha256":"f36b207d39a0f07a","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"MLPNetwork","code_sha256":"d91c262ff01c1192","role":"helper","order":6,"level":1,"status":"ran"},{"entry":"OUNoise","code_sha256":"5a6b141fd404c7c4","role":"helper","order":7,"level":1,"status":"ran"},{"entry":"hard_update","code_sha256":"e6250f15677e1203","role":"helper","order":8,"level":0,"status":"unverified"},{"entry":"gumbel_softmax_sample","code_sha256":"6697676fd57aebe3","role":"helper","order":9,"level":1,"status":"ran_draft_wrong"},{"entry":"sample_gumbel","code_sha256":"43c7e814609746ee","role":"helper","order":10,"level":1,"status":"ran_draft_wrong"}],"ran_individually":6,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":2,"ran_draft_wrong":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"d8c5ad0642a476bd","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The code implements a multi-agent actor-critic algorithm where each agent has its own actor and critic networks, and the critic is conditioned on the observations and actions of all agents to address non-stationarity in multi-agent environments.","centrality":"contribution","entry":"MADDPG","entry_sha256":"00f4c151df8ceb67","n_bricks":3,"bricks":[{"entry":"MADDPG","code_sha256":"00f4c151df8ceb67","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"b1b715fc5cea22be","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"601cec5195b4709d","role":"model","order":2,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"d9354f221d6787ec","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The paper proposes a multi-agent actor-critic method where agents learn decentralized policies with a centralized critic that has access to all agents' observations and actions.","centrality":"contribution","entry":"MADDPG","entry_sha256":"98101e244acd71e0","n_bricks":5,"bricks":[{"entry":"MADDPG","code_sha256":"98101e244acd71e0","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"DDPGAgent","code_sha256":"4471e9be4006d33f","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"MultiAgentReplayBuffer","code_sha256":"053976ac8304e4a8","role":"sampler","order":2,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"19cc670e3070c844","role":"model","order":3,"level":1,"status":"ran"},{"entry":"CentralizedCritic","code_sha256":"5809fd7ddfdc55c2","role":"model","order":4,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"e2975ac65ff9a792","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The code implements a multi-agent actor-critic algorithm where each agent has its own actor and critic networks, and the critics are trained using the observations and actions of all agents to address environment non-stationarity.","centrality":"contribution","entry":"MADDPG","entry_sha256":"ba0b5facd7c2091a","n_bricks":5,"bricks":[{"entry":"MADDPG","code_sha256":"ba0b5facd7c2091a","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"cbd481c5cf284628","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"0d8d2fce5fa8c834","role":"model","order":2,"level":1,"status":"ran"},{"entry":"ReplayMemory","code_sha256":"14185602fbb4fa11","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"soft_update","code_sha256":"f0ba29ce2b116d79","role":"update_rule","order":4,"level":0,"status":"unverified"}],"ran_individually":3,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ebe5736503ac7fcc","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The paper proposes a multi-agent actor-critic method where each agent's policy (actor) and value function (critic) are learned in a centralized training with decentralized execution framework.","centrality":"contribution","entry":"Actor","entry_sha256":"e0a77db60f82cb02","n_bricks":1,"bricks":[{"entry":"Actor","code_sha256":"e0a77db60f82cb02","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"f2d3546c2874a360","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The paper proposes a multi-agent actor-critic method where the critic model estimates the value function for decentralized policies in mixed cooperative-competitive environments.","centrality":"contribution","entry":"get_critic","entry_sha256":"3b0d740d86579224","n_bricks":1,"bricks":[{"entry":"get_critic","code_sha256":"3b0d740d86579224","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"fb220d477eee1017","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The paper proposes a multi-agent actor-critic method (MADDPG) that extends DDPG to handle mixed cooperative-competitive environments by using centralized training with decentralized execution.","centrality":"contribution","entry":"MADDPG","entry_sha256":"8064ffc41e0e0c2e","n_bricks":8,"bricks":[{"entry":"MADDPG","code_sha256":"8064ffc41e0e0c2e","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor_Critic_Models","code_sha256":"1b5ce00b5c4ba8e0","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"DDPG","code_sha256":"dc719785d5a0b9f7","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"0fe6e65cdf5950a9","role":"sampler","order":3,"level":0,"status":"unverified"},{"entry":"ActorModel","code_sha256":"7153bd2279c31cfb","role":"model","order":4,"level":1,"status":"ran"},{"entry":"CriticModel","code_sha256":"1e89d38fb0c5b84b","role":"model","order":5,"level":1,"status":"ran"},{"entry":"OUNoise","code_sha256":"0562ed655f21cba8","role":"helper","order":6,"level":1,"status":"ran"},{"entry":"hidden_init","code_sha256":"24ee38e114b38bce","role":"helper","order":7,"level":1,"status":"ran_honours"}],"ran_individually":5,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":4,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"fb700643b1f781f1","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The code implements a multi-agent actor-critic method where each agent's policy is trained with a centralized critic that has access to all agents' observations and actions, addressing non-stationarity in multi-agent environments.","centrality":"contribution","entry":"MADDPG","entry_sha256":"f02f8f35b7849439","n_bricks":11,"bricks":[{"entry":"MADDPG","code_sha256":"f02f8f35b7849439","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"DDPGAgent","code_sha256":"798b209df2b695ff","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"average_gradients","code_sha256":"a3e542c9d6910a27","role":"helper","order":2,"level":0,"status":"unverified"},{"entry":"gumbel_softmax","code_sha256":"57d033c0c861f3d0","role":"helper","order":3,"level":1,"status":"ran_draft_wrong"},{"entry":"onehot_from_logits","code_sha256":"f925a8c266bb2532","role":"helper","order":4,"level":1,"status":"ran_draft_wrong"},{"entry":"soft_update","code_sha256":"f36b207d39a0f07a","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"MLPNetwork","code_sha256":"d91c262ff01c1192","role":"helper","order":6,"level":1,"status":"ran"},{"entry":"OUNoise","code_sha256":"5a6b141fd404c7c4","role":"helper","order":7,"level":1,"status":"ran"},{"entry":"hard_update","code_sha256":"e6250f15677e1203","role":"helper","order":8,"level":0,"status":"unverified"},{"entry":"gumbel_softmax_sample","code_sha256":"6697676fd57aebe3","role":"helper","order":9,"level":1,"status":"ran_draft_wrong"},{"entry":"sample_gumbel","code_sha256":"43c7e814609746ee","role":"helper","order":10,"level":1,"status":"ran_draft_wrong"}],"ran_individually":6,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":2,"ran_draft_wrong":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"fd2e13aaabe4f0d0","source_kind":"harvested","method_name":"Multi-Agent Actor-Critic","realizes_method":"Multi-Agent Actor-Critic","graph_method":"Multi-Agent Actor-Critic","realizes_severed":false,"claim":"The paper proposes a multi-agent actor-critic method where the critic estimates the value of state-action pairs for all agents to address non-stationarity and high variance in multi-agent environments.","centrality":"contribution","entry":"Critic","entry_sha256":"e9875c7422df7fec","n_bricks":1,"bricks":[{"entry":"Critic","code_sha256":"e9875c7422df7fec","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"9cc3526d0915","n_siblings":27,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"}],"assembly_sibling_groups":[{"group":"9cc3526d0915","realizes_method":"Multi-Agent Actor-Critic","source_kind":"harvested","batch_at":"2026-09-09T22:44:46+00:00","members":["08dfe679226d8a4c","1b8f52ac0b2e8498","1d5c41798982399a","2d6cce03875d9bbb","2e507cae3bc95110","47fc82edd0105864","4982b5225173dc2c","50d65724740a3248","61e234a490fff2b4","7e6cbb8b82abd9ee","8062b0816299b3a2","8d0ba20acebdbfcb","9c15b02245652b8a","a5801506ae9dbb86","acd0f0cb49555d04","b63df89ac823bf96","cc6438be33b63b66","cd5c698f587b9e16","cfb588886b6d696e","d2cdce2d3b6b4440","d8c5ad0642a476bd","d9354f221d6787ec","e2975ac65ff9a792","ebe5736503ac7fcc","f2d3546c2874a360","fb220d477eee1017","fb700643b1f781f1","fd2e13aaabe4f0d0"]}],"assemblies_is":{"about":"What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results.","harvested":"assembled from code harvested from a repository linked to the paper","generated":"generated from the paper text, not the repository's code","end_to_end":"for a harvested assembly, the assembly has not been run end-to-end; for a generated one, end_to_end.level is the assembly's own level and against_independent_peer says whether it ran against a peer: an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists","bricks_level":"each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level","ran_individually":"a COUNT of bricks that ran on their own on a fixture (split by status in ran_individually_by_status), not a level; instrument statuses are failures of Syntology's instrument, not of the code","siblings":"assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another","judged":"Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as \"by construction\" or \"not judged by a model\"","level_lowered":"a generated assembly whose level Syntology's graph lowered, with the level it had, the recorded reason and when","retention":"Syntology's spending triage for further verification, not a verdict","claim_match":"the claim_match vote: IMPLEMENTS, COMPONENT or UNCLEAR. Where claim_match_basis is \"judge:<model>\", it is one model's judgement of the assembly's label against the paper's claim (claim_match_rule single_judge, the model in claim_match_judges): not a verification and not a run. Where it is \"construction\", the value was set when the code was generated for this method and no model judged it, whatever claim_match_rule says. The page prints no claim match for any assembly","label_verdict":"whether the assembly's code is the method it is labelled with: matches, cannot_tell, mislabelled (suggested_method names what it looks like instead) or not_the_method; label_verdict_judged is true only when a model read the code (claim_match_basis \"judge:<model>\")","label_verdict_judged":"where true (claim_match_basis \"judge:<model>\"), label_verdict is a single model's judgement; not calibrated; not printed on the page; where false, it was set by construction, and the page prints it unless the node is shared with another paper (node_properties_written_for)","claim":"the claim text stored on the assembly node: for a harvested assembly, what the paper claims the code implements, as the lifting model wrote it; for a generated one, the specification the code was generated from. Not verified text","centrality":"how central the lifted method is to the paper, as the lifting step recorded it: contribution, component or incidental","v3_tests_passed_both_sides":"end_to_end.v3_tests_passed_both_sides: the number of property tests derived from the paper that passed on both implementations, as the attached report lists them; a level 3 card with 0 says its report lists none","ran_individually_constructed":"ran_individually_constructed: of the bricks counted in ran_individually, how many constructed an object rather than computing a result (Syntology's RAN record's rule, read from the graph-layer sample with the brick's code_sha256); a part of ran_individually, never subtracted from it and never a failure; null where a brick that ran has no sample in the graph layer this build read, so the figure was not counted"},"assemblies_call":{"tool":"assembly","arguments":{"arxiv_id":"1706.02275"},"call":"assembly(arxiv_id=\"1706.02275\")"},"read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/1706.02275.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/1706.02275.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/semitable/multiagent-particle-envs","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tkarr21/multagent-particle-envs","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/darshil333/CSE574","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qi-pang/mdpfuzz","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bonniesjli/MADDPG_Tennis","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gingkg/multiagent-particle-envs","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jyqhahah/rl_maddpg_matd3","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NeuroCSUT/intentions","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bonniesjli/MADDPG_Tennis_UnityML","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ray-project/ray/tree/master/rllib","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/krasing/DRLearningCollaboration","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rainandwind1/MERL","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kishorkuttan/Multi-Agent-Deep-Deterministic-Policy-Gradient-actor-critic-deep-reinforcement-for-capacity-manageme","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shariqiqbal2810/maddpg-pytorch","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cyoon1729/Multi-agent-reinforcement-learning","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wsjeon/multiagent-particle-envs-maac","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openai/maddpg","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cyanrain7/trust-region-policy-optimisation-in-multi-agent-reinforcement-learning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/goldbattle/snakes_mal","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marwanihab/RL_Testing_Noise_ASRN","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AleXander-Tsui/MPE","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jingdic/rgmcomm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LXYYY/multiagent-particle-envs","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zowiezhang/stas","reach":{"status":"ok"}}],"summary":{"ran":66,"ran_draft_wrong":6,"ran_honours":2,"ran_fixture":1,"unverified":68},"n_samples":143,"n_ran":75,"n_constructed":54,"n_ran_checked":68,"n_instrument":7,"n_unverified":68,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"listed":{"samples":142,"ran":74,"n_ran_checked":67,"n_instrument":7,"repositories":29},"unlocated":{"samples":1,"ran":1,"n_ran_checked":1,"n_instrument":0,"repositories":0,"is":"identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded"}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"official_not_harvested":{"repositories":["openai/multiagent-particle-envs"],"harvested_for_other_papers":[0],"samples_from_other_repositories":142,"other_repositories":29,"samples_unlocated":1},"n_pointer_only_for_licence":99,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing","signature_not_shown":"the graph records a signature for this sample and it is not shown; signature_not_shown_because names why, as the export's field-exclusion reason","signature_not_shown_because":{"signature_is_harness_probe_not_fixture_args":"for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments"}},"n_ran_with_level_date":75,"n_ran_without_level_date":0,"n_ran_signature_not_shown":20,"levels_written_between":{"first":"2026-09-22","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","census_is":"Syntology's function-name census ran implementations with this entry name on one shared input per bucket (the positional rank, kind and dtype of each array argument) and counted the distinct output digests (sha256 of the output rounded to 6 decimals). implementations and papers count the compared samples; distinct_outputs counts digests across all buckets; n_buckets is how many shared inputs were used. It is not a statement that any two samples compute one thing, and the name is a string, not an identity.","samples":[{"code_sha256":"788933ff608baaea","code_sha256_prefix":"788933ff608baaea","entry":"ACTLayer","repo":"anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","repo_kind":"listed","path":"algorithms/happo_policy.py","file_url":"https://github.com/anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning/blob/HEAD/algorithms/happo_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"ACTLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"788933ff608baaea"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"788933ff608baaea"}},{"code_sha256":"d33580612fa8578d","code_sha256_prefix":"d33580612fa8578d","entry":"Actor","repo":"zowiezhang/stas","repo_kind":"listed","path":"models/policy/COMA.py","file_url":"https://github.com/zowiezhang/stas/blob/HEAD/models/policy/COMA.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"d33580612fa8578d"},"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zowiezhang/stas when it was checked","mcp_get_code":{"code_sha256":"d33580612fa8578d"}},{"code_sha256":"394e91b566a8e7eb","code_sha256_prefix":"394e91b566a8e7eb","entry":"Actor","repo":"rainandwind1/MADDPG-reconstruct","repo_kind":"listed","path":"MADDPG/model.py","file_url":"https://github.com/rainandwind1/MADDPG-reconstruct/blob/HEAD/MADDPG/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"394e91b566a8e7eb"},"code_page":"/code/actor","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"394e91b566a8e7eb"}},{"code_sha256":"147d57177bbffdd9","code_sha256_prefix":"147d57177bbffdd9","entry":"Actor","repo":"MrDaubinet/collaboration-and-competition","repo_kind":"listed","path":"maddpg.py","file_url":"https://github.com/MrDaubinet/collaboration-and-competition/blob/HEAD/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"147d57177bbffdd9"},"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, MrDaubinet/collaboration-and-competition when it was checked","mcp_get_code":{"code_sha256":"147d57177bbffdd9"}},{"code_sha256":"b1b715fc5cea22be","code_sha256_prefix":"b1b715fc5cea22be","entry":"Actor","repo":"starry-sky6688/MADDPG","repo_kind":"listed","path":"maddpg/maddpg.py","file_url":"https://github.com/starry-sky6688/MADDPG/blob/HEAD/maddpg/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"b1b715fc5cea22be"},"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, starry-sky6688/MADDPG when it was checked","mcp_get_code":{"code_sha256":"b1b715fc5cea22be"}},{"code_sha256":"ab8b87babe2b659e","code_sha256_prefix":"ab8b87babe2b659e","entry":"Actor","repo":"krasing/DRLearningCollaboration","repo_kind":"listed","path":"failed_collaborative/ddpg_agent_multi_2.py","file_url":"https://github.com/krasing/DRLearningCollaboration/blob/HEAD/failed_collaborative/ddpg_agent_multi_2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"ab8b87babe2b659e"},"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, krasing/DRLearningCollaboration when it was checked","mcp_get_code":{"code_sha256":"ab8b87babe2b659e"}},{"code_sha256":"a17bd67f978b7355","code_sha256_prefix":"a17bd67f978b7355","entry":"Actor","repo":"petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity","repo_kind":"listed","path":"multiagent_resources.py","file_url":"https://github.com/petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity/blob/HEAD/multiagent_resources.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"a17bd67f978b7355"},"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity when it was checked","mcp_get_code":{"code_sha256":"a17bd67f978b7355"}},{"code_sha256":"cbd481c5cf284628","code_sha256_prefix":"cbd481c5cf284628","entry":"Actor","repo":"isp1tze/MAProj","repo_kind":"listed","path":"algo/maddpg/maddpg_agent.py","file_url":"https://github.com/isp1tze/MAProj/blob/HEAD/algo/maddpg/maddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"cbd481c5cf284628"},"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, isp1tze/MAProj when it was checked","mcp_get_code":{"code_sha256":"cbd481c5cf284628"}},{"code_sha256":"af7b2cc00bcf3971","code_sha256_prefix":"af7b2cc00bcf3971","entry":"Actor","repo":"bonniesjli/MADDPG_Tennis_UnityML","repo_kind":"listed","path":"MADDPG.py","file_url":"https://github.com/bonniesjli/MADDPG_Tennis_UnityML/blob/HEAD/MADDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"af7b2cc00bcf3971"},"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, bonniesjli/MADDPG_Tennis_UnityML when it was checked","mcp_get_code":{"code_sha256":"af7b2cc00bcf3971"}},{"code_sha256":"19cc670e3070c844","code_sha256_prefix":"19cc670e3070c844","entry":"Actor","repo":"thechrisyoon08/marl","repo_kind":"listed","path":"MADDPG/maddpg.py","file_url":"https://github.com/thechrisyoon08/marl/blob/HEAD/MADDPG/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"obs:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"19cc670e3070c844"},"code_page":"/code/actor","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"19cc670e3070c844"}},{"code_sha256":"e0a77db60f82cb02","code_sha256_prefix":"e0a77db60f82cb02","entry":"Actor","repo":"Ah31/maddpg_pytorch","repo_kind":"listed","path":"MADDPG_model.py","file_url":"https://github.com/Ah31/maddpg_pytorch/blob/HEAD/MADDPG_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"state:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"e0a77db60f82cb02"},"code_page":"/code/actor","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e0a77db60f82cb02"}},{"code_sha256":"7153bd2279c31cfb","code_sha256_prefix":"7153bd2279c31cfb","entry":"ActorModel","repo":"EyaRhouma/collaboration-competition-MADDPG","repo_kind":"listed","path":"MADDPG_agent.py","file_url":"https://github.com/EyaRhouma/collaboration-competition-MADDPG/blob/HEAD/MADDPG_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"state:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"7153bd2279c31cfb"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, EyaRhouma/collaboration-competition-MADDPG when it was checked","mcp_get_code":{"code_sha256":"7153bd2279c31cfb"}},{"code_sha256":"5d2b3c4f1fd1a9f4","code_sha256_prefix":"5d2b3c4f1fd1a9f4","entry":"ActorNetwork","repo":"baradist/multiagent-particle-envs","repo_kind":"listed","path":"multiagent/ddpg/ddpg_agent.py","file_url":"https://github.com/baradist/multiagent-particle-envs/blob/HEAD/multiagent/ddpg/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"ActorNetwork","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"5d2b3c4f1fd1a9f4"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5d2b3c4f1fd1a9f4"}},{"code_sha256":"19dd2e9c270f0dc6","code_sha256_prefix":"19dd2e9c270f0dc6","entry":"ActorNetwork","repo":"philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients","repo_kind":"listed","path":"maddpg.py","file_url":"https://github.com/philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients/blob/HEAD/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"ActorNetwork","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"19dd2e9c270f0dc6"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients when it was checked","mcp_get_code":{"code_sha256":"19dd2e9c270f0dc6"}},{"code_sha256":"6e3b52a2c0014b70","code_sha256_prefix":"6e3b52a2c0014b70","entry":"Agent","repo":"philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients","repo_kind":"listed","path":"maddpg.py","file_url":"https://github.com/philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients/blob/HEAD/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Agent","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients when it was checked","mcp_get_code":{"code_sha256":"6e3b52a2c0014b70"}},{"code_sha256":"23a16fcf13d93070","code_sha256_prefix":"23a16fcf13d93070","entry":"AttentionCritic","repo":"Chan1998/MAAC","repo_kind":"listed","path":"algorithms/attention_sac.py","file_url":"https://github.com/Chan1998/MAAC/blob/HEAD/algorithms/attention_sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"AttentionCritic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Chan1998/MAAC (NOASSERTION)","mcp_get_code":{"code_sha256":"23a16fcf13d93070"}},{"code_sha256":"e3579cc107de4c0a","code_sha256_prefix":"e3579cc107de4c0a","entry":"BasePolicy","repo":"Chan1998/MAAC","repo_kind":"listed","path":"algorithms/attention_sac.py","file_url":"https://github.com/Chan1998/MAAC/blob/HEAD/algorithms/attention_sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"BasePolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/basepolicy","census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Chan1998/MAAC (NOASSERTION)","mcp_get_code":{"code_sha256":"e3579cc107de4c0a"}},{"code_sha256":"ce4cd71349aedb12","code_sha256_prefix":"ce4cd71349aedb12","entry":"Bernoulli","repo":"anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","repo_kind":"listed","path":"algorithms/happo_policy.py","file_url":"https://github.com/anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning/blob/HEAD/algorithms/happo_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Bernoulli","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/bernoulli-2","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ce4cd71349aedb12"}},{"code_sha256":"e6b6fc2b3a05ee48","code_sha256_prefix":"e6b6fc2b3a05ee48","entry":"COMA","repo":"zowiezhang/stas","repo_kind":"listed","path":"models/policy/COMA.py","file_url":"https://github.com/zowiezhang/stas/blob/HEAD/models/policy/COMA.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"COMA","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zowiezhang/stas when it was checked","mcp_get_code":{"code_sha256":"e6b6fc2b3a05ee48"}},{"code_sha256":"5809fd7ddfdc55c2","code_sha256_prefix":"5809fd7ddfdc55c2","entry":"CentralizedCritic","repo":"thechrisyoon08/marl","repo_kind":"listed","path":"MADDPG/maddpg.py","file_url":"https://github.com/thechrisyoon08/marl/blob/HEAD/MADDPG/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"x:Tensor/2/float, a:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5809fd7ddfdc55c2"}},{"code_sha256":"6879c98b93ce7112","code_sha256_prefix":"6879c98b93ce7112","entry":"Critic","repo":"zowiezhang/stas","repo_kind":"listed","path":"models/policy/COMA.py","file_url":"https://github.com/zowiezhang/stas/blob/HEAD/models/policy/COMA.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zowiezhang/stas when it was checked","mcp_get_code":{"code_sha256":"6879c98b93ce7112"}},{"code_sha256":"30449e98cba1cf61","code_sha256_prefix":"30449e98cba1cf61","entry":"Critic","repo":"rainandwind1/MADDPG-reconstruct","repo_kind":"listed","path":"MADDPG/model.py","file_url":"https://github.com/rainandwind1/MADDPG-reconstruct/blob/HEAD/MADDPG/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"30449e98cba1cf61"},"code_page":"/code/critic","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"30449e98cba1cf61"}},{"code_sha256":"6c1f59af0972c70e","code_sha256_prefix":"6c1f59af0972c70e","entry":"Critic","repo":"MrDaubinet/collaboration-and-competition","repo_kind":"listed","path":"maddpg.py","file_url":"https://github.com/MrDaubinet/collaboration-and-competition/blob/HEAD/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, MrDaubinet/collaboration-and-competition when it was checked","mcp_get_code":{"code_sha256":"6c1f59af0972c70e"}},{"code_sha256":"601cec5195b4709d","code_sha256_prefix":"601cec5195b4709d","entry":"Critic","repo":"starry-sky6688/MADDPG","repo_kind":"listed","path":"maddpg/maddpg.py","file_url":"https://github.com/starry-sky6688/MADDPG/blob/HEAD/maddpg/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, starry-sky6688/MADDPG when it was checked","mcp_get_code":{"code_sha256":"601cec5195b4709d"}},{"code_sha256":"9af882c88cb87dda","code_sha256_prefix":"9af882c88cb87dda","entry":"Critic","repo":"krasing/DRLearningCollaboration","repo_kind":"listed","path":"failed_collaborative/ddpg_agent_multi_2.py","file_url":"https://github.com/krasing/DRLearningCollaboration/blob/HEAD/failed_collaborative/ddpg_agent_multi_2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, krasing/DRLearningCollaboration when it was checked","mcp_get_code":{"code_sha256":"9af882c88cb87dda"}},{"code_sha256":"6d943b1d04649de3","code_sha256_prefix":"6d943b1d04649de3","entry":"Critic","repo":"petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity","repo_kind":"listed","path":"multiagent_resources.py","file_url":"https://github.com/petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity/blob/HEAD/multiagent_resources.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity when it was checked","mcp_get_code":{"code_sha256":"6d943b1d04649de3"}},{"code_sha256":"0d8d2fce5fa8c834","code_sha256_prefix":"0d8d2fce5fa8c834","entry":"Critic","repo":"isp1tze/MAProj","repo_kind":"listed","path":"algo/maddpg/maddpg_agent.py","file_url":"https://github.com/isp1tze/MAProj/blob/HEAD/algo/maddpg/maddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, isp1tze/MAProj when it was checked","mcp_get_code":{"code_sha256":"0d8d2fce5fa8c834"}},{"code_sha256":"a7f0fe3c4dffccc9","code_sha256_prefix":"a7f0fe3c4dffccc9","entry":"Critic","repo":"xuehy/pytorch-maddpg","repo_kind":"listed","path":"MADDPG.py","file_url":"https://github.com/xuehy/pytorch-maddpg/blob/HEAD/MADDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xuehy/pytorch-maddpg when it was checked","mcp_get_code":{"code_sha256":"a7f0fe3c4dffccc9"}},{"code_sha256":"b89abb00e73f1560","code_sha256_prefix":"b89abb00e73f1560","entry":"Critic","repo":"bonniesjli/MADDPG_Tennis_UnityML","repo_kind":"listed","path":"MADDPG.py","file_url":"https://github.com/bonniesjli/MADDPG_Tennis_UnityML/blob/HEAD/MADDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, bonniesjli/MADDPG_Tennis_UnityML when it was checked","mcp_get_code":{"code_sha256":"b89abb00e73f1560"}},{"code_sha256":"1e89d38fb0c5b84b","code_sha256_prefix":"1e89d38fb0c5b84b","entry":"CriticModel","repo":"EyaRhouma/collaboration-competition-MADDPG","repo_kind":"listed","path":"MADDPG_agent.py","file_url":"https://github.com/EyaRhouma/collaboration-competition-MADDPG/blob/HEAD/MADDPG_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"states:Tensor/2/float, actions:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, EyaRhouma/collaboration-competition-MADDPG when it was checked","mcp_get_code":{"code_sha256":"1e89d38fb0c5b84b"}},{"code_sha256":"619856d2049bc612","code_sha256_prefix":"619856d2049bc612","entry":"CriticNetwork","repo":"baradist/multiagent-particle-envs","repo_kind":"listed","path":"multiagent/ddpg/ddpg_agent.py","file_url":"https://github.com/baradist/multiagent-particle-envs/blob/HEAD/multiagent/ddpg/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"CriticNetwork","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/criticnetwork","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"619856d2049bc612"}},{"code_sha256":"1a6507f0b27d66e3","code_sha256_prefix":"1a6507f0b27d66e3","entry":"CriticNetwork","repo":"philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients","repo_kind":"listed","path":"maddpg.py","file_url":"https://github.com/philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients/blob/HEAD/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"CriticNetwork","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/criticnetwork","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients when it was checked","mcp_get_code":{"code_sha256":"1a6507f0b27d66e3"}},{"code_sha256":"bbf8b2fce98ed3c3","code_sha256_prefix":"bbf8b2fce98ed3c3","entry":"DDPGAgent","repo":"biemann/Collaboration-and-Competition","repo_kind":"listed","path":"maddpg.py","file_url":"https://github.com/biemann/Collaboration-and-Competition/blob/HEAD/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"DDPGAgent","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ddpgagent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, biemann/Collaboration-and-Competition when it was checked","mcp_get_code":{"code_sha256":"bbf8b2fce98ed3c3"}},{"code_sha256":"4471e9be4006d33f","code_sha256_prefix":"4471e9be4006d33f","entry":"DDPGAgent","repo":"thechrisyoon08/marl","repo_kind":"listed","path":"MADDPG/maddpg.py","file_url":"https://github.com/thechrisyoon08/marl/blob/HEAD/MADDPG/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"indiv_reward_batch:ndarray/1/float, indiv_obs_batch:ndarray/2/float, global_state_batch:ndarray/2/float, global_actions_batch:list/1/Tensor, global_next_state_batch:ndarray/2/float, next_global_actions:Tensor/2/float","fixture_out_type":"NoneType","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/ddpgagent","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4471e9be4006d33f"}},{"code_sha256":"6072c4350e278037","code_sha256_prefix":"6072c4350e278037","entry":"DiagGaussian","repo":"anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","repo_kind":"listed","path":"algorithms/happo_policy.py","file_url":"https://github.com/anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning/blob/HEAD/algorithms/happo_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"DiagGaussian","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6072c4350e278037"}},{"code_sha256":"b4fe457a99be3144","code_sha256_prefix":"b4fe457a99be3144","entry":"DiscretePolicy","repo":"Chan1998/MAAC","repo_kind":"listed","path":"algorithms/attention_sac.py","file_url":"https://github.com/Chan1998/MAAC/blob/HEAD/algorithms/attention_sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"obs:Tensor/2/float, sample:bool/0/bool, return_all_probs:bool/0/bool, return_log_pi:bool/0/bool, regularize:bool/0/bool, return_entropy:bool/0/bool","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Chan1998/MAAC (NOASSERTION)","mcp_get_code":{"code_sha256":"b4fe457a99be3144"}},{"code_sha256":"b4481f38bbb906b5","code_sha256_prefix":"b4481f38bbb906b5","entry":"ExperienceBuffer","repo":"petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity","repo_kind":"listed","path":"multiagent_resources.py","file_url":"https://github.com/petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity/blob/HEAD/multiagent_resources.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ExperienceBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity when it was checked","mcp_get_code":{"code_sha256":"b4481f38bbb906b5"}},{"code_sha256":"a48b952a1d356122","code_sha256_prefix":"a48b952a1d356122","entry":"FixedBernoulli","repo":"anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","repo_kind":"listed","path":"algorithms/happo_policy.py","file_url":"https://github.com/anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning/blob/HEAD/algorithms/happo_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"FixedBernoulli","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a48b952a1d356122"}},{"code_sha256":"2430b3c71fa829d4","code_sha256_prefix":"2430b3c71fa829d4","entry":"FixedNormal","repo":"anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","repo_kind":"listed","path":"algorithms/happo_policy.py","file_url":"https://github.com/anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning/blob/HEAD/algorithms/happo_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"FixedNormal","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2430b3c71fa829d4"}},{"code_sha256":"14f32d9aecd1c394","code_sha256_prefix":"14f32d9aecd1c394","entry":"HAPPO","repo":"morning9393/HAPPO-HATRPO","repo_kind":"listed","path":"algorithms/happo_trainer.py","file_url":"https://github.com/morning9393/HAPPO-HATRPO/blob/HEAD/algorithms/happo_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"HAPPO","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"14f32d9aecd1c394"}},{"code_sha256":"a3dd086ac1fbb639","code_sha256_prefix":"a3dd086ac1fbb639","entry":"MADDPG","repo":"biemann/Collaboration-and-Competition","repo_kind":"listed","path":"maddpg.py","file_url":"https://github.com/biemann/Collaboration-and-Competition/blob/HEAD/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"state_all_agents:list/1/Tensor, noise:float/0/float","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, biemann/Collaboration-and-Competition when it was checked","mcp_get_code":{"code_sha256":"a3dd086ac1fbb639"}},{"code_sha256":"cc58450c6eb52f3a","code_sha256_prefix":"cc58450c6eb52f3a","entry":"MADDPG","repo":"isp1tze/MAProj","repo_kind":"listed","path":"algo/maddpg/maddpg_agent.py","file_url":"https://github.com/isp1tze/MAProj/blob/HEAD/algo/maddpg/maddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"MADDPG","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, isp1tze/MAProj when it was checked","mcp_get_code":{"code_sha256":"cc58450c6eb52f3a"}},{"code_sha256":"bcbd9c4a35e9a9e0","code_sha256_prefix":"bcbd9c4a35e9a9e0","entry":"MADDPG","repo":"xuehy/pytorch-maddpg","repo_kind":"listed","path":"MADDPG.py","file_url":"https://github.com/xuehy/pytorch-maddpg/blob/HEAD/MADDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"MADDPG","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xuehy/pytorch-maddpg when it was checked","mcp_get_code":{"code_sha256":"bcbd9c4a35e9a9e0"}},{"code_sha256":"af4f065d2ca09a90","code_sha256_prefix":"af4f065d2ca09a90","entry":"MADDPG","repo":"philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients","repo_kind":"listed","path":"maddpg.py","file_url":"https://github.com/philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients/blob/HEAD/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"MADDPG","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients when it was checked","mcp_get_code":{"code_sha256":"af4f065d2ca09a90"}},{"code_sha256":"eb97113b662895e7","code_sha256_prefix":"eb97113b662895e7","entry":"MLPBase","repo":"anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","repo_kind":"listed","path":"algorithms/happo_policy.py","file_url":"https://github.com/anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning/blob/HEAD/algorithms/happo_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"MLPBase","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"eb97113b662895e7"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"eb97113b662895e7"}},{"code_sha256":"052cdd66a800bf26","code_sha256_prefix":"052cdd66a800bf26","entry":"MLPLayer","repo":"anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","repo_kind":"listed","path":"algorithms/happo_policy.py","file_url":"https://github.com/anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning/blob/HEAD/algorithms/happo_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"MLPLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/mlplayer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"052cdd66a800bf26"}},{"code_sha256":"d91c262ff01c1192","code_sha256_prefix":"d91c262ff01c1192","entry":"MLPNetwork","repo":"Yutongamber/MADDPG","repo_kind":"listed","path":"maddpg-pytorch/algorithms/maddpg.py","file_url":"https://github.com/Yutongamber/MADDPG/blob/HEAD/maddpg-pytorch/algorithms/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"X:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/mlpnetwork","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d91c262ff01c1192"}},{"code_sha256":"51c877df80bace64","code_sha256_prefix":"51c877df80bace64","entry":"Memory","repo":"zowiezhang/stas","repo_kind":"listed","path":"models/policy/COMA.py","file_url":"https://github.com/zowiezhang/stas/blob/HEAD/models/policy/COMA.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Memory","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/memory","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zowiezhang/stas when it was checked","mcp_get_code":{"code_sha256":"51c877df80bace64"}},{"code_sha256":"f6fceb14173df844","code_sha256_prefix":"f6fceb14173df844","entry":"Network","repo":"biemann/Collaboration-and-Competition","repo_kind":"listed","path":"maddpg.py","file_url":"https://github.com/biemann/Collaboration-and-Competition/blob/HEAD/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Network","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/network","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, biemann/Collaboration-and-Competition when it was checked","mcp_get_code":{"code_sha256":"f6fceb14173df844"}},{"code_sha256":"1ea60fdd30545832","code_sha256_prefix":"1ea60fdd30545832","entry":"OUActionNoise","repo":"baradist/multiagent-particle-envs","repo_kind":"listed","path":"multiagent/ddpg/ddpg_agent.py","file_url":"https://github.com/baradist/multiagent-particle-envs/blob/HEAD/multiagent/ddpg/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUActionNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1ea60fdd30545832"}},{"code_sha256":"458174da77a0b0ce","code_sha256_prefix":"458174da77a0b0ce","entry":"OUActionNoise","repo":"petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity","repo_kind":"listed","path":"multiagent_resources.py","file_url":"https://github.com/petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity/blob/HEAD/multiagent_resources.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUActionNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity when it was checked","mcp_get_code":{"code_sha256":"458174da77a0b0ce"}},{"code_sha256":"db3bd13d21d6150c","code_sha256_prefix":"db3bd13d21d6150c","entry":"OUNoise","repo":"MrDaubinet/collaboration-and-competition","repo_kind":"listed","path":"maddpg.py","file_url":"https://github.com/MrDaubinet/collaboration-and-competition/blob/HEAD/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ounoise","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, MrDaubinet/collaboration-and-competition when it was checked","mcp_get_code":{"code_sha256":"db3bd13d21d6150c"}},{"code_sha256":"555ae48ebffc59d4","code_sha256_prefix":"555ae48ebffc59d4","entry":"OUNoise","repo":"biemann/Collaboration-and-Competition","repo_kind":"listed","path":"maddpg.py","file_url":"https://github.com/biemann/Collaboration-and-Competition/blob/HEAD/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ounoise","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, biemann/Collaboration-and-Competition when it was checked","mcp_get_code":{"code_sha256":"555ae48ebffc59d4"}},{"code_sha256":"a169b2555a871836","code_sha256_prefix":"a169b2555a871836","entry":"OUNoise","repo":"krasing/DRLearningCollaboration","repo_kind":"listed","path":"failed_collaborative/ddpg_agent_multi_2.py","file_url":"https://github.com/krasing/DRLearningCollaboration/blob/HEAD/failed_collaborative/ddpg_agent_multi_2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ounoise","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, krasing/DRLearningCollaboration when it was checked","mcp_get_code":{"code_sha256":"a169b2555a871836"}},{"code_sha256":"bab2a198c923111d","code_sha256_prefix":"bab2a198c923111d","entry":"PlacholderTfInput","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"data:Tensor/2/float","fixture_out_type":"dict","level_recorded_at":"2026-09-24T16:18:31.416280+00:00","retrieve_with":{"tool":"get_code","code_sha256":"bab2a198c923111d"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"bab2a198c923111d"}},{"code_sha256":"cf971b9dc43b13b4","code_sha256_prefix":"cf971b9dc43b13b4","entry":"PopArt","repo":"morning9393/HAPPO-HATRPO","repo_kind":"listed","path":"algorithms/happo_trainer.py","file_url":"https://github.com/morning9393/HAPPO-HATRPO/blob/HEAD/algorithms/happo_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"PopArt","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"cf971b9dc43b13b4"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"cf971b9dc43b13b4"}},{"code_sha256":"ff5a06e4902f81ab","code_sha256_prefix":"ff5a06e4902f81ab","entry":"RNNLayer","repo":"anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","repo_kind":"listed","path":"algorithms/happo_policy.py","file_url":"https://github.com/anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning/blob/HEAD/algorithms/happo_policy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"RNNLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ff5a06e4902f81ab"}},{"code_sha256":"ae26aa48075ee6cb","code_sha256_prefix":"ae26aa48075ee6cb","entry":"ReplayBuffer","repo":"MrDaubinet/collaboration-and-competition","repo_kind":"listed","path":"maddpg.py","file_url":"https://github.com/MrDaubinet/collaboration-and-competition/blob/HEAD/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, MrDaubinet/collaboration-and-competition when it was checked","mcp_get_code":{"code_sha256":"ae26aa48075ee6cb"}},{"code_sha256":"c90519f77627be1f","code_sha256_prefix":"c90519f77627be1f","entry":"ReplayBuffer","repo":"baradist/multiagent-particle-envs","repo_kind":"listed","path":"multiagent/ddpg/ddpg_agent.py","file_url":"https://github.com/baradist/multiagent-particle-envs/blob/HEAD/multiagent/ddpg/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c90519f77627be1f"}},{"code_sha256":"4cbc44a206f6120a","code_sha256_prefix":"4cbc44a206f6120a","entry":"ReplayBuffer","repo":"krasing/DRLearningCollaboration","repo_kind":"listed","path":"failed_collaborative/ddpg_agent_multi_2.py","file_url":"https://github.com/krasing/DRLearningCollaboration/blob/HEAD/failed_collaborative/ddpg_agent_multi_2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, krasing/DRLearningCollaboration when it was checked","mcp_get_code":{"code_sha256":"4cbc44a206f6120a"}},{"code_sha256":"21d74b782714cf9e","code_sha256_prefix":"21d74b782714cf9e","entry":"ReplayBuffer","repo":"bonniesjli/MADDPG_Tennis_UnityML","repo_kind":"listed","path":"MADDPG.py","file_url":"https://github.com/bonniesjli/MADDPG_Tennis_UnityML/blob/HEAD/MADDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, bonniesjli/MADDPG_Tennis_UnityML when it was checked","mcp_get_code":{"code_sha256":"21d74b782714cf9e"}},{"code_sha256":"14185602fbb4fa11","code_sha256_prefix":"14185602fbb4fa11","entry":"ReplayMemory","repo":"isp1tze/MAProj","repo_kind":"listed","path":"algo/maddpg/maddpg_agent.py","file_url":"https://github.com/isp1tze/MAProj/blob/HEAD/algo/maddpg/maddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayMemory","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaymemory","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, isp1tze/MAProj when it was checked","mcp_get_code":{"code_sha256":"14185602fbb4fa11"}},{"code_sha256":"535c542a4e41bb65","code_sha256_prefix":"535c542a4e41bb65","entry":"ReplayMemory","repo":"xuehy/pytorch-maddpg","repo_kind":"listed","path":"MADDPG.py","file_url":"https://github.com/xuehy/pytorch-maddpg/blob/HEAD/MADDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayMemory","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaymemory","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xuehy/pytorch-maddpg when it was checked","mcp_get_code":{"code_sha256":"535c542a4e41bb65"}},{"code_sha256":"74c1bafecdee5848","code_sha256_prefix":"74c1bafecdee5848","entry":"Replaybuffer","repo":"rainandwind1/MADDPG-reconstruct","repo_kind":"listed","path":"MADDPG/model.py","file_url":"https://github.com/rainandwind1/MADDPG-reconstruct/blob/HEAD/MADDPG/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Replaybuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"74c1bafecdee5848"}},{"code_sha256":"9cf2b925ec95c7f2","code_sha256_prefix":"9cf2b925ec95c7f2","entry":"SoftCategoricalPdType","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"flat:EagerTensor/2/float","fixture_out_type":"SoftCategoricalPd","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"9cf2b925ec95c7f2"}},{"code_sha256":"8a12d52820205fa8","code_sha256_prefix":"8a12d52820205fa8","entry":"categorical_sample","repo":"Chan1998/MAAC","repo_kind":"listed","path":"algorithms/attention_sac.py","file_url":"https://github.com/Chan1998/MAAC/blob/HEAD/algorithms/attention_sac.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"probs:Tensor/2/float, use_cuda:bool/0/bool","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"8a12d52820205fa8"},"code_page":"/code/categorical-sample","census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Chan1998/MAAC (NOASSERTION)","mcp_get_code":{"code_sha256":"8a12d52820205fa8"}},{"code_sha256":"9589eca5bae9de80","code_sha256_prefix":"9589eca5bae9de80","entry":"check","repo":"morning9393/HAPPO-HATRPO","repo_kind":"listed","path":"algorithms/happo_trainer.py","file_url":"https://github.com/morning9393/HAPPO-HATRPO/blob/HEAD/algorithms/happo_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"input:ndarray/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/check","census":{"url":"/census/check","implementations":5,"papers":6,"distinct_outputs":4,"n_buckets":4,"bucket_key":[[2,"float","float32"]],"bucket_index":1,"bucket_label":"arg 1: rank 2, kind float, dtype float32"},"census_bucket_fragment":"bucket-1","licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9589eca5bae9de80"}},{"code_sha256":"57d033c0c861f3d0","code_sha256_prefix":"57d033c0c861f3d0","entry":"gumbel_softmax","repo":"Yutongamber/MADDPG","repo_kind":"listed","path":"maddpg-pytorch/algorithms/maddpg.py","file_url":"https://github.com/Yutongamber/MADDPG/blob/HEAD/maddpg-pytorch/algorithms/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"logits:Tensor/2/float, temperature:float/0/float, hard:bool/0/bool","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"57d033c0c861f3d0"},"code_page":"/code/gumbel-softmax","census":{"url":"/census/gumbel-softmax","implementations":19,"papers":20,"distinct_outputs":12,"n_buckets":2,"bucket_key":[[2,"float","float32"]],"bucket_index":1,"bucket_label":"arg 1: rank 2, kind float, dtype float32"},"census_bucket_fragment":"bucket-1","licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"57d033c0c861f3d0"}},{"code_sha256":"6697676fd57aebe3","code_sha256_prefix":"6697676fd57aebe3","entry":"gumbel_softmax_sample","repo":"Yutongamber/MADDPG","repo_kind":"listed","path":"maddpg-pytorch/algorithms/maddpg.py","file_url":"https://github.com/Yutongamber/MADDPG/blob/HEAD/maddpg-pytorch/algorithms/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"logits:Tensor/2/float, temperature:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"6697676fd57aebe3"},"code_page":"/code/gumbel-softmax-sample","census":{"url":"/census/gumbel-softmax-sample","implementations":14,"papers":16,"distinct_outputs":4,"n_buckets":1,"bucket_key":[[2,"float","float32"]],"bucket_index":1,"bucket_label":"arg 1: rank 2, kind float, dtype float32"},"census_bucket_fragment":"bucket-1","licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6697676fd57aebe3"}},{"code_sha256":"24ee38e114b38bce","code_sha256_prefix":"24ee38e114b38bce","entry":"hidden_init","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"signature":"layer:callable/0/?","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/hidden-init","census":null,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"24ee38e114b38bce"}},{"code_sha256":"51c9fbcd079c6fda","code_sha256_prefix":"51c9fbcd079c6fda","entry":"minimize_and_clip","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Operation","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"51c9fbcd079c6fda"}},{"code_sha256":"5290a0543b38c4dc","code_sha256_prefix":"5290a0543b38c4dc","entry":"onehot_from_logits","repo":"Chan1998/MAAC","repo_kind":"listed","path":"algorithms/attention_sac.py","file_url":"https://github.com/Chan1998/MAAC/blob/HEAD/algorithms/attention_sac.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"logits:Tensor/2/float, eps:float/0/float, dim:int/0/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"5290a0543b38c4dc"},"code_page":"/code/onehot-from-logits","census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Chan1998/MAAC (NOASSERTION)","mcp_get_code":{"code_sha256":"5290a0543b38c4dc"}},{"code_sha256":"f925a8c266bb2532","code_sha256_prefix":"f925a8c266bb2532","entry":"onehot_from_logits","repo":"Yutongamber/MADDPG","repo_kind":"listed","path":"maddpg-pytorch/algorithms/maddpg.py","file_url":"https://github.com/Yutongamber/MADDPG/blob/HEAD/maddpg-pytorch/algorithms/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"logits:Tensor/2/float, eps:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"f925a8c266bb2532"},"code_page":"/code/onehot-from-logits","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f925a8c266bb2532"}},{"code_sha256":"43c7e814609746ee","code_sha256_prefix":"43c7e814609746ee","entry":"sample_gumbel","repo":"Yutongamber/MADDPG","repo_kind":"listed","path":"maddpg-pytorch/algorithms/maddpg.py","file_url":"https://github.com/Yutongamber/MADDPG/blob/HEAD/maddpg-pytorch/algorithms/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"shape:tuple/1/int, eps:float/0/float, tens_type:tensortype/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/sample-gumbel","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"43c7e814609746ee"}},{"code_sha256":"61d3f2ae09e0df23","code_sha256_prefix":"61d3f2ae09e0df23","entry":"softmax","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"x:EagerTensor/2/float, axis:NoneType/0/?","fixture_out_type":"EagerTensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"61d3f2ae09e0df23"},"code_page":"/code/softmax","census":{"url":"/census/softmax","implementations":53,"papers":63,"distinct_outputs":16,"n_buckets":8,"bucket_key":null,"bucket_index":null,"bucket_label":null},"census_bucket_fragment":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"61d3f2ae09e0df23"}},{"code_sha256":"85e19366b66e12c8","code_sha256_prefix":"85e19366b66e12c8","entry":"Actor","repo":"ksajan/DDPG-MAPE","repo_kind":"listed","path":"multiagent-particle-envs/maddpg.py","file_url":"https://github.com/ksajan/DDPG-MAPE/blob/HEAD/multiagent-particle-envs/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ksajan/DDPG-MAPE when it was checked","mcp_get_code":{"code_sha256":"85e19366b66e12c8"}},{"code_sha256":"fe0a30f4af252b51","code_sha256_prefix":"fe0a30f4af252b51","entry":"Actor","repo":"anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","repo_kind":"listed","path":"algorithms/happo_policy.py","file_url":"https://github.com/anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning/blob/HEAD/algorithms/happo_policy.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actor","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"fe0a30f4af252b51"}},{"code_sha256":"1b5ce00b5c4ba8e0","code_sha256_prefix":"1b5ce00b5c4ba8e0","entry":"Actor_Critic_Models","repo":"EyaRhouma/collaboration-competition-MADDPG","repo_kind":"listed","path":"MADDPG_agent.py","file_url":"https://github.com/EyaRhouma/collaboration-competition-MADDPG/blob/HEAD/MADDPG_agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, EyaRhouma/collaboration-competition-MADDPG when it was checked","mcp_get_code":{"code_sha256":"1b5ce00b5c4ba8e0"}},{"code_sha256":"5d2d3b9ff319eb0d","code_sha256_prefix":"5d2d3b9ff319eb0d","entry":"Agent","repo":"MrDaubinet/collaboration-and-competition","repo_kind":"listed","path":"maddpg.py","file_url":"https://github.com/MrDaubinet/collaboration-and-competition/blob/HEAD/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, MrDaubinet/collaboration-and-competition when it was checked","mcp_get_code":{"code_sha256":"5d2d3b9ff319eb0d"}},{"code_sha256":"f3e14c78a36f2168","code_sha256_prefix":"f3e14c78a36f2168","entry":"Agent","repo":"baradist/multiagent-particle-envs","repo_kind":"listed","path":"multiagent/ddpg/ddpg_agent.py","file_url":"https://github.com/baradist/multiagent-particle-envs/blob/HEAD/multiagent/ddpg/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f3e14c78a36f2168"}},{"code_sha256":"a35198f4b2a98333","code_sha256_prefix":"a35198f4b2a98333","entry":"Agent","repo":"petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity","repo_kind":"listed","path":"multiagent_resources.py","file_url":"https://github.com/petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity/blob/HEAD/multiagent_resources.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity when it was checked","mcp_get_code":{"code_sha256":"a35198f4b2a98333"}},{"code_sha256":"c455aad4cf9e3d68","code_sha256_prefix":"c455aad4cf9e3d68","entry":"Agent","repo":"bonniesjli/MADDPG_Tennis_UnityML","repo_kind":"listed","path":"MADDPG.py","file_url":"https://github.com/bonniesjli/MADDPG_Tennis_UnityML/blob/HEAD/MADDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, bonniesjli/MADDPG_Tennis_UnityML when it was checked","mcp_get_code":{"code_sha256":"c455aad4cf9e3d68"}},{"code_sha256":"d0b7f852c271a2cb","code_sha256_prefix":"d0b7f852c271a2cb","entry":"AgentTrainer","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"d0b7f852c271a2cb"}},{"code_sha256":"ce87b1d927fb04e1","code_sha256_prefix":"ce87b1d927fb04e1","entry":"Agents","repo":"krasing/DRLearningCollaboration","repo_kind":"listed","path":"failed_collaborative/ddpg_agent_multi_2.py","file_url":"https://github.com/krasing/DRLearningCollaboration/blob/HEAD/failed_collaborative/ddpg_agent_multi_2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, krasing/DRLearningCollaboration when it was checked","mcp_get_code":{"code_sha256":"ce87b1d927fb04e1"}},{"code_sha256":"5e7a8abdf83466de","code_sha256_prefix":"5e7a8abdf83466de","entry":"AttentionAgent","repo":"Chan1998/MAAC","repo_kind":"listed","path":"algorithms/attention_sac.py","file_url":"https://github.com/Chan1998/MAAC/blob/HEAD/algorithms/attention_sac.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Chan1998/MAAC (NOASSERTION)","mcp_get_code":{"code_sha256":"5e7a8abdf83466de"}},{"code_sha256":"92865550d0fc369e","code_sha256_prefix":"92865550d0fc369e","entry":"AttentionSAC","repo":"Chan1998/MAAC","repo_kind":"listed","path":"algorithms/attention_sac.py","file_url":"https://github.com/Chan1998/MAAC/blob/HEAD/algorithms/attention_sac.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Chan1998/MAAC (NOASSERTION)","mcp_get_code":{"code_sha256":"92865550d0fc369e"}},{"code_sha256":"410b8121d522d60d","code_sha256_prefix":"410b8121d522d60d","entry":"BatchInput","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"410b8121d522d60d"}},{"code_sha256":"7855bf32a05f6453","code_sha256_prefix":"7855bf32a05f6453","entry":"BernoulliPd","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"7855bf32a05f6453"}},{"code_sha256":"04989e6ce54eef99","code_sha256_prefix":"04989e6ce54eef99","entry":"BernoulliPdType","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"04989e6ce54eef99"}},{"code_sha256":"598a59b21df91031","code_sha256_prefix":"598a59b21df91031","entry":"Critic","repo":"anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","repo_kind":"listed","path":"algorithms/happo_policy.py","file_url":"https://github.com/anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning/blob/HEAD/algorithms/happo_policy.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/critic","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"598a59b21df91031"}},{"code_sha256":"e9875c7422df7fec","code_sha256_prefix":"e9875c7422df7fec","entry":"Critic","repo":"johannesharmse/multi_agent_RL","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/johannesharmse/multi_agent_RL/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/critic","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e9875c7422df7fec"}},{"code_sha256":"a3a587bc7fe0ee77","code_sha256_prefix":"a3a587bc7fe0ee77","entry":"DDPG","repo":"rainandwind1/MADDPG-reconstruct","repo_kind":"listed","path":"MADDPG/model.py","file_url":"https://github.com/rainandwind1/MADDPG-reconstruct/blob/HEAD/MADDPG/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a3a587bc7fe0ee77"}},{"code_sha256":"a4bedfc0dceee998","code_sha256_prefix":"a4bedfc0dceee998","entry":"DDPG","repo":"rainandwind1/Maddpg_multiagent","repo_kind":"listed","path":"model.py","file_url":"https://github.com/rainandwind1/Maddpg_multiagent/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a4bedfc0dceee998"}},{"code_sha256":"23ccb70277ce98c1","code_sha256_prefix":"23ccb70277ce98c1","entry":"DDPGAgent","repo":"Yutongamber/MADDPG","repo_kind":"listed","path":"maddpg-pytorch/algorithms/maddpg.py","file_url":"https://github.com/Yutongamber/MADDPG/blob/HEAD/maddpg-pytorch/algorithms/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/ddpgagent","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"23ccb70277ce98c1"}},{"code_sha256":"798b209df2b695ff","code_sha256_prefix":"798b209df2b695ff","entry":"DDPGAgent","repo":"mauricemager/multiagent-robot","repo_kind":"listed","path":"algorithms/maddpg.py","file_url":"https://github.com/mauricemager/multiagent-robot/blob/HEAD/algorithms/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/ddpgagent","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"798b209df2b695ff"}},{"code_sha256":"99ab37a0b854f64c","code_sha256_prefix":"99ab37a0b854f64c","entry":"DiagGaussianPd","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"99ab37a0b854f64c"}},{"code_sha256":"9c5f519b1107c4a0","code_sha256_prefix":"9c5f519b1107c4a0","entry":"DiagGaussianPdType","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"9c5f519b1107c4a0"}},{"code_sha256":"972d50b722edcc62","code_sha256_prefix":"972d50b722edcc62","entry":"HAPPO","repo":"cyanrain7/trpo-in-marl","repo_kind":"listed","path":"algorithms/happo_trainer.py","file_url":"https://github.com/cyanrain7/trpo-in-marl/blob/HEAD/algorithms/happo_trainer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"972d50b722edcc62"}},{"code_sha256":"a78bf4c700ca5bb9","code_sha256_prefix":"a78bf4c700ca5bb9","entry":"HAPPO_Policy","repo":"anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","repo_kind":"listed","path":"algorithms/happo_policy.py","file_url":"https://github.com/anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning/blob/HEAD/algorithms/happo_policy.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a78bf4c700ca5bb9"}},{"code_sha256":"9bc56ac4d586a2d2","code_sha256_prefix":"9bc56ac4d586a2d2","entry":"MADDPG","repo":"rainandwind1/MADDPG-reconstruct","repo_kind":"listed","path":"MADDPG/model.py","file_url":"https://github.com/rainandwind1/MADDPG-reconstruct/blob/HEAD/MADDPG/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9bc56ac4d586a2d2"}},{"code_sha256":"6551e7add10520be","code_sha256_prefix":"6551e7add10520be","entry":"MADDPG","repo":"MrDaubinet/collaboration-and-competition","repo_kind":"listed","path":"maddpg.py","file_url":"https://github.com/MrDaubinet/collaboration-and-competition/blob/HEAD/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, MrDaubinet/collaboration-and-competition when it was checked","mcp_get_code":{"code_sha256":"6551e7add10520be"}},{"code_sha256":"eb82e9aa0da99b86","code_sha256_prefix":"eb82e9aa0da99b86","entry":"MADDPG","repo":"starry-sky6688/MADDPG","repo_kind":"listed","path":"maddpg/maddpg.py","file_url":"https://github.com/starry-sky6688/MADDPG/blob/HEAD/maddpg/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, starry-sky6688/MADDPG when it was checked","mcp_get_code":{"code_sha256":"eb82e9aa0da99b86"}},{"code_sha256":"b38b019a971f0e14","code_sha256_prefix":"b38b019a971f0e14","entry":"MADDPG","repo":"bonniesjli/MADDPG_Tennis_UnityML","repo_kind":"listed","path":"MADDPG.py","file_url":"https://github.com/bonniesjli/MADDPG_Tennis_UnityML/blob/HEAD/MADDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, bonniesjli/MADDPG_Tennis_UnityML when it was checked","mcp_get_code":{"code_sha256":"b38b019a971f0e14"}},{"code_sha256":"6c6569c6b5d38959","code_sha256_prefix":"6c6569c6b5d38959","entry":"MADDPG","repo":"Abdelhamid-bouzid/Multi-Agent-Deep-Deterministic-Policy-Gradient","repo_kind":"listed","path":"maddpg.py","file_url":"https://github.com/Abdelhamid-bouzid/Multi-Agent-Deep-Deterministic-Policy-Gradient/blob/HEAD/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Abdelhamid-bouzid/Multi-Agent-Deep-Deterministic-Policy-Gradient when it was checked","mcp_get_code":{"code_sha256":"6c6569c6b5d38959"}},{"code_sha256":"05a2c85c2c068627","code_sha256_prefix":"05a2c85c2c068627","entry":"MADDPG","repo":"Yutongamber/MADDPG","repo_kind":"listed","path":"maddpg-pytorch/algorithms/maddpg.py","file_url":"https://github.com/Yutongamber/MADDPG/blob/HEAD/maddpg-pytorch/algorithms/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"05a2c85c2c068627"}},{"code_sha256":"00f4c151df8ceb67","code_sha256_prefix":"00f4c151df8ceb67","entry":"MADDPG","repo":"jingdic/rgmcomm","repo_kind":"listed","path":"RGMComm_stage1/maddpg/maddpg.py","file_url":"https://github.com/jingdic/rgmcomm/blob/HEAD/RGMComm_stage1/maddpg/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, jingdic/rgmcomm when it was checked","mcp_get_code":{"code_sha256":"00f4c151df8ceb67"}},{"code_sha256":"98101e244acd71e0","code_sha256_prefix":"98101e244acd71e0","entry":"MADDPG","repo":"thechrisyoon08/marl","repo_kind":"listed","path":"MADDPG/maddpg.py","file_url":"https://github.com/thechrisyoon08/marl/blob/HEAD/MADDPG/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"98101e244acd71e0"}},{"code_sha256":"ba0b5facd7c2091a","code_sha256_prefix":"ba0b5facd7c2091a","entry":"MADDPG","repo":"jyqhahah/rl_maddpg_matd3","repo_kind":"listed","path":"algo/maddpg/maddpg_agent.py","file_url":"https://github.com/jyqhahah/rl_maddpg_matd3/blob/HEAD/algo/maddpg/maddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, jyqhahah/rl_maddpg_matd3 when it was checked","mcp_get_code":{"code_sha256":"ba0b5facd7c2091a"}},{"code_sha256":"8064ffc41e0e0c2e","code_sha256_prefix":"8064ffc41e0e0c2e","entry":"MADDPG","repo":"EyaRhouma/collaboration-competition-MADDPG","repo_kind":"listed","path":"MADDPG_agent.py","file_url":"https://github.com/EyaRhouma/collaboration-competition-MADDPG/blob/HEAD/MADDPG_agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, EyaRhouma/collaboration-competition-MADDPG when it was checked","mcp_get_code":{"code_sha256":"8064ffc41e0e0c2e"}},{"code_sha256":"f02f8f35b7849439","code_sha256_prefix":"f02f8f35b7849439","entry":"MADDPG","repo":"mauricemager/multiagent-robot","repo_kind":"listed","path":"algorithms/maddpg.py","file_url":"https://github.com/mauricemager/multiagent-robot/blob/HEAD/algorithms/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f02f8f35b7849439"}},{"code_sha256":"b2f7329c7900cbee","code_sha256_prefix":"b2f7329c7900cbee","entry":"MADDPGAgentTrainer","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"b2f7329c7900cbee"}},{"code_sha256":"053976ac8304e4a8","code_sha256_prefix":"053976ac8304e4a8","entry":"MultiAgentReplayBuffer","repo":"thechrisyoon08/marl","repo_kind":"listed","path":"MADDPG/maddpg.py","file_url":"https://github.com/thechrisyoon08/marl/blob/HEAD/MADDPG/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"053976ac8304e4a8"}},{"code_sha256":"19525957eb332eb2","code_sha256_prefix":"19525957eb332eb2","entry":"MultiDiscrete","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"19525957eb332eb2"}},{"code_sha256":"26b44f96043b4296","code_sha256_prefix":"26b44f96043b4296","entry":"Pd","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"26b44f96043b4296"}},{"code_sha256":"a233d862ed1c5de8","code_sha256_prefix":"a233d862ed1c5de8","entry":"PdType","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"a233d862ed1c5de8"}},{"code_sha256":"0ec668ec81ebce4d","code_sha256_prefix":"0ec668ec81ebce4d","entry":"ReplayBuffer","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/replaybuffer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"0ec668ec81ebce4d"}},{"code_sha256":"0fe6e65cdf5950a9","code_sha256_prefix":"0fe6e65cdf5950a9","entry":"ReplayBuffer","repo":"EyaRhouma/collaboration-competition-MADDPG","repo_kind":"listed","path":"MADDPG_agent.py","file_url":"https://github.com/EyaRhouma/collaboration-competition-MADDPG/blob/HEAD/MADDPG_agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/replaybuffer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, EyaRhouma/collaboration-competition-MADDPG when it was checked","mcp_get_code":{"code_sha256":"0fe6e65cdf5950a9"}},{"code_sha256":"1fe728fdf693afaf","code_sha256_prefix":"1fe728fdf693afaf","entry":"SoftCategoricalPd","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"1fe728fdf693afaf"}},{"code_sha256":"9bb22eb75cfa28b6","code_sha256_prefix":"9bb22eb75cfa28b6","entry":"SoftMultiCategoricalPd","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"9bb22eb75cfa28b6"}},{"code_sha256":"8371d56181f23309","code_sha256_prefix":"8371d56181f23309","entry":"SoftMultiCategoricalPdType","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"8371d56181f23309"}},{"code_sha256":"654b5868fdbabd66","code_sha256_prefix":"654b5868fdbabd66","entry":"TfInput","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"654b5868fdbabd66"}},{"code_sha256":"8523867a9c545bdf","code_sha256_prefix":"8523867a9c545bdf","entry":"_Function","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"8523867a9c545bdf"}},{"code_sha256":"0f6bbf3f67ac6f9c","code_sha256_prefix":"0f6bbf3f67ac6f9c","entry":"absolute_scope_name","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"0f6bbf3f67ac6f9c"}},{"code_sha256":"a3e542c9d6910a27","code_sha256_prefix":"a3e542c9d6910a27","entry":"average_gradients","repo":"Yutongamber/MADDPG","repo_kind":"listed","path":"maddpg-pytorch/algorithms/maddpg.py","file_url":"https://github.com/Yutongamber/MADDPG/blob/HEAD/maddpg-pytorch/algorithms/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/average-gradients","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a3e542c9d6910a27"}},{"code_sha256":"34bbc966346baa78","code_sha256_prefix":"34bbc966346baa78","entry":"disable_gradients","repo":"Chan1998/MAAC","repo_kind":"listed","path":"algorithms/attention_sac.py","file_url":"https://github.com/Chan1998/MAAC/blob/HEAD/algorithms/attention_sac.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Chan1998/MAAC (NOASSERTION)","mcp_get_code":{"code_sha256":"34bbc966346baa78"}},{"code_sha256":"8e93ecfbcd3abb77","code_sha256_prefix":"8e93ecfbcd3abb77","entry":"enable_gradients","repo":"Chan1998/MAAC","repo_kind":"listed","path":"algorithms/attention_sac.py","file_url":"https://github.com/Chan1998/MAAC/blob/HEAD/algorithms/attention_sac.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Chan1998/MAAC (NOASSERTION)","mcp_get_code":{"code_sha256":"8e93ecfbcd3abb77"}},{"code_sha256":"5b6a9e8f5134b90d","code_sha256_prefix":"5b6a9e8f5134b90d","entry":"function","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/function","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"5b6a9e8f5134b90d"}},{"code_sha256":"3b0d740d86579224","code_sha256_prefix":"3b0d740d86579224","entry":"get_critic","repo":"pr-shukla/maddpg-keras","repo_kind":"listed","path":"maddpg/model.py","file_url":"https://github.com/pr-shukla/maddpg-keras/blob/HEAD/maddpg/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3b0d740d86579224"}},{"code_sha256":"61c6759fad1b2459","code_sha256_prefix":"61c6759fad1b2459","entry":"get_session","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"61c6759fad1b2459"}},{"code_sha256":"e6250f15677e1203","code_sha256_prefix":"e6250f15677e1203","entry":"hard_update","repo":"Chan1998/MAAC","repo_kind":"listed","path":"algorithms/attention_sac.py","file_url":"https://github.com/Chan1998/MAAC/blob/HEAD/algorithms/attention_sac.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Chan1998/MAAC (NOASSERTION)","mcp_get_code":{"code_sha256":"e6250f15677e1203"}},{"code_sha256":"7e5ebeb6de3d3d4a","code_sha256_prefix":"7e5ebeb6de3d3d4a","entry":"is_placeholder","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"7e5ebeb6de3d3d4a"}},{"code_sha256":"731751ece9e0b766","code_sha256_prefix":"731751ece9e0b766","entry":"make_pdtype","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"731751ece9e0b766"}},{"code_sha256":"0d1a79fa849ba189","code_sha256_prefix":"0d1a79fa849ba189","entry":"make_update_exp","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"0d1a79fa849ba189"}},{"code_sha256":"cc0b8c4aa9b99165","code_sha256_prefix":"cc0b8c4aa9b99165","entry":"max","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"cc0b8c4aa9b99165"}},{"code_sha256":"8ebadf88476f8efe","code_sha256_prefix":"8ebadf88476f8efe","entry":"mean","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/mean","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"8ebadf88476f8efe"}},{"code_sha256":"79a21c888d914a27","code_sha256_prefix":"79a21c888d914a27","entry":"p_train","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"79a21c888d914a27"}},{"code_sha256":"e03118d1752f94fe","code_sha256_prefix":"e03118d1752f94fe","entry":"q_train","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"e03118d1752f94fe"}},{"code_sha256":"706116fa3e5a5a6c","code_sha256_prefix":"706116fa3e5a5a6c","entry":"scope_name","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"706116fa3e5a5a6c"}},{"code_sha256":"de2061bedccd8dc9","code_sha256_prefix":"de2061bedccd8dc9","entry":"scope_vars","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"de2061bedccd8dc9"}},{"code_sha256":"f36b207d39a0f07a","code_sha256_prefix":"f36b207d39a0f07a","entry":"soft_update","repo":"Chan1998/MAAC","repo_kind":"listed","path":"algorithms/attention_sac.py","file_url":"https://github.com/Chan1998/MAAC/blob/HEAD/algorithms/attention_sac.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/soft-update","census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, Chan1998/MAAC (NOASSERTION)","mcp_get_code":{"code_sha256":"f36b207d39a0f07a"}},{"code_sha256":"f0ba29ce2b116d79","code_sha256_prefix":"f0ba29ce2b116d79","entry":"soft_update","repo":"isp1tze/MAProj","repo_kind":"listed","path":"algo/maddpg/maddpg_agent.py","file_url":"https://github.com/isp1tze/MAProj/blob/HEAD/algo/maddpg/maddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/soft-update","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, isp1tze/MAProj when it was checked","mcp_get_code":{"code_sha256":"f0ba29ce2b116d79"}},{"code_sha256":"fbab233112bf4d1e","code_sha256_prefix":"fbab233112bf4d1e","entry":"sum","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/sum","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"fbab233112bf4d1e"}},{"code_sha256":"598184a2689d36d0","code_sha256_prefix":"598184a2689d36d0","entry":"var","repo":"baoqianwang/iros22_darl1n","repo_kind":"listed","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/var","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, baoqianwang/iros22_darl1n when it was checked","mcp_get_code":{"code_sha256":"598184a2689d36d0"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"e8f6f2a04508783f464e81e6f8064da794a103f2ced0ab2d1fe9190570199a24","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}