{"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":"/dataset/smac-def-infantry-sequential","name":"Def_Infantry_sequential","full_name":null,"description_markdown":"SMAC+ defensive infantry scenario with sequential episodic buffer","description_withheld":null,"homepage":"","introduced_date":"2022-07-05","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-starcraft-multi-agent-challenges-learning","title":"The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions","first_author":"Mingyu Kim","url":null},"license":null,"modalities":[],"tasks":[{"name":"SMAC+","url":"/task/smac-1","datasets_with_task":"/datasets/task/smac-1"}],"languages":[],"variants":["Def_Infantry_sequential"],"data_loaders":[],"num_papers_in_archive":9,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/smac-on-smac-def-infantry-sequential","task":"SMAC+","dataset_variant":"Def_Infantry_sequential","rows":11,"metrics":["Median Win Rate"],"first_row_in_archive_order":{"model":"MADDPG","paper":"/paper/multi-agent-actor-critic-for-mixed","metrics":{"Median Win Rate":"100"},"code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"openai/multiagent-particle-envs","url":"https://github.com/openai/multiagent-particle-envs"},{"title":"openai/maddpg","url":"https://github.com/openai/maddpg"},{"title":"xuehy/pytorch-maddpg","url":"https://github.com/xuehy/pytorch-maddpg"},{"title":"shariqiqbal2810/maddpg-pytorch","url":"https://github.com/shariqiqbal2810/maddpg-pytorch"},{"title":"starry-sky6688/MADDPG","url":"https://github.com/starry-sky6688/MADDPG"},{"title":"facebookresearch/benchmarl","url":"https://github.com/facebookresearch/benchmarl"},{"title":"philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients","url":"https://github.com/philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients"},{"title":"cyanrain7/trpo-in-marl","url":"https://github.com/cyanrain7/trpo-in-marl"},{"title":"cyanrain7/trust-region-policy-optimisation-in-multi-agent-reinforcement-learning","url":"https://github.com/cyanrain7/trust-region-policy-optimisation-in-multi-agent-reinforcement-learning"},{"title":"JohannesAck/tf2multiagentrl","url":"https://github.com/JohannesAck/tf2multiagentrl"},{"title":"isp1tze/MAProj","url":"https://github.com/isp1tze/MAProj"},{"title":"JohannesAck/MATD3implementation","url":"https://github.com/JohannesAck/MATD3implementation"},{"title":"thechrisyoon08/Multi-agent-reinforcement-learning","url":"https://github.com/thechrisyoon08/Multi-agent-reinforcement-learning"},{"title":"thechrisyoon08/marl","url":"https://github.com/thechrisyoon08/marl"},{"title":"cyoon1729/Multi-agent-reinforcement-learning","url":"https://github.com/cyoon1729/Multi-agent-reinforcement-learning"},{"title":"quantumiracle/mars","url":"https://github.com/quantumiracle/mars"},{"title":"shariqiqbal2810/multiagent-particle-envs","url":"https://github.com/shariqiqbal2810/multiagent-particle-envs"},{"title":"morning9393/HAPPO-HATRPO","url":"https://github.com/morning9393/HAPPO-HATRPO"},{"title":"google/maddpg-replication","url":"https://github.com/google/maddpg-replication"},{"title":"caslab-vt/SARNet","url":"https://github.com/caslab-vt/SARNet"},{"title":"qi-pang/mdpfuzz","url":"https://github.com/qi-pang/mdpfuzz"},{"title":"pr-shukla/maddpg-keras","url":"https://github.com/pr-shukla/maddpg-keras"},{"title":"gingkg/multiagent-particle-envs","url":"https://github.com/gingkg/multiagent-particle-envs"},{"title":"jyqhahah/rl_maddpg_matd3","url":"https://github.com/jyqhahah/rl_maddpg_matd3"},{"title":"baoqianwang/iros22_darl1n","url":"https://github.com/baoqianwang/iros22_darl1n"},{"title":"zowiezhang/stas","url":"https://github.com/zowiezhang/stas"},{"title":"yannbouteiller/gym-airsimdroneracinglab","url":"https://github.com/yannbouteiller/gym-airsimdroneracinglab"},{"title":"anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","url":"https://github.com/anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning"},{"title":"schroederdewitt/multiagent-particle-envs","url":"https://github.com/schroederdewitt/multiagent-particle-envs"},{"title":"EyaRhouma/collaboration-competition-MADDPG","url":"https://github.com/EyaRhouma/collaboration-competition-MADDPG"},{"title":"zoeyuchao/MPE-pytorch","url":"https://github.com/zoeyuchao/MPE-pytorch"},{"title":"bonniesjli/MADDPG_Tennis","url":"https://github.com/bonniesjli/MADDPG_Tennis"},{"title":"bonniesjli/MADDPG_Tennis_UnityML","url":"https://github.com/bonniesjli/MADDPG_Tennis_UnityML"},{"title":"semitable/multiagent-particle-envs","url":"https://github.com/semitable/multiagent-particle-envs"},{"title":"kargarisaac/macrpo","url":"https://github.com/kargarisaac/macrpo"},{"title":"madras-simulator/Multi-Agent-Particle-Environment","url":"https://github.com/madras-simulator/Multi-Agent-Particle-Environment"},{"title":"wsjeon/multiagent-particle-envs-maac","url":"https://github.com/wsjeon/multiagent-particle-envs-maac"},{"title":"NeuroCSUT/intentions","url":"https://github.com/NeuroCSUT/intentions"},{"title":"marwanihab/RL_Tag_Game","url":"https://github.com/marwanihab/RL_Tag_Game"},{"title":"zoeyuchao/MPEnew-pytorch","url":"https://github.com/zoeyuchao/MPEnew-pytorch"},{"title":"lachisis/multiagent-particle-envs","url":"https://github.com/lachisis/multiagent-particle-envs"},{"title":"Stippler/cow-simulator","url":"https://github.com/Stippler/cow-simulator"},{"title":"biorobotics/PRD_environments","url":"https://github.com/biorobotics/PRD_environments"},{"title":"raoshashank/Tennis-with-MADDPG","url":"https://github.com/raoshashank/Tennis-with-MADDPG"},{"title":"Steven-Ho/multiagent-particle-envs","url":"https://github.com/Steven-Ho/multiagent-particle-envs"},{"title":"sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3","url":"https://github.com/sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3"},{"title":"Ah31/maddpg_pytorch","url":"https://github.com/Ah31/maddpg_pytorch"},{"title":"karishnu/tf-agents-multi-particle-envs","url":"https://github.com/karishnu/tf-agents-multi-particle-envs"},{"title":"SihongHo/multiagent-particle-envs","url":"https://github.com/SihongHo/multiagent-particle-envs"},{"title":"wsjeon/multiagent-particle-envs-v2","url":"https://github.com/wsjeon/multiagent-particle-envs-v2"},{"title":"baicenxiao/shaping-advice","url":"https://github.com/baicenxiao/shaping-advice"},{"title":"Yutongamber/MADDPG","url":"https://github.com/Yutongamber/MADDPG"},{"title":"SintolRTOS/multi-agent_Example","url":"https://github.com/SintolRTOS/multi-agent_Example"},{"title":"Chan1998/MAAC","url":"https://github.com/Chan1998/MAAC"},{"title":"Abdelhamid-bouzid/Multi-Agent-Deep-Deterministic-Policy-Gradient","url":"https://github.com/Abdelhamid-bouzid/Multi-Agent-Deep-Deterministic-Policy-Gradient"},{"title":"debajit15kgp/multiagent-envs","url":"https://github.com/debajit15kgp/multiagent-envs"},{"title":"johannesharmse/multi_agent_RL","url":"https://github.com/johannesharmse/multi_agent_RL"},{"title":"jingdic/rgmcomm","url":"https://github.com/jingdic/rgmcomm"},{"title":"rainandwind1/Maddpg_multiagent","url":"https://github.com/rainandwind1/Maddpg_multiagent"},{"title":"kishorkuttan/Multi-Agent-Deep-Deterministic-Policy-Gradient-actor-critic-deep-reinforcement-for-capacity-manageme","url":"https://github.com/kishorkuttan/Multi-Agent-Deep-Deterministic-Policy-Gradient-actor-critic-deep-reinforcement-for-capacity-manageme"},{"title":"dtabas/multiagent-particle-envs","url":"https://github.com/dtabas/multiagent-particle-envs"},{"title":"goldbattle/snakes_mal","url":"https://github.com/goldbattle/snakes_mal"},{"title":"ksajan/DDPG-MAPE","url":"https://github.com/ksajan/DDPG-MAPE"},{"title":"rainandwind1/MERL","url":"https://github.com/rainandwind1/MERL"},{"title":"darshil333/CSE574","url":"https://github.com/darshil333/CSE574"},{"title":"rallen10/multiagent-particle-envs","url":"https://github.com/rallen10/multiagent-particle-envs"},{"title":"tkarr21/multagent-particle-envs","url":"https://github.com/tkarr21/multagent-particle-envs"},{"title":"mauricemager/multiagent-robot","url":"https://github.com/mauricemager/multiagent-robot"},{"title":"tkarr21/multiagent-particle-envs","url":"https://github.com/tkarr21/multiagent-particle-envs"},{"title":"petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity","url":"https://github.com/petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity"},{"title":"MrDaubinet/collaboration-and-competition","url":"https://github.com/MrDaubinet/collaboration-and-competition"},{"title":"LXYYY/multiagent-particle-envs","url":"https://github.com/LXYYY/multiagent-particle-envs"},{"title":"Zorrorulz/MultiAgentDDPG-Tennis","url":"https://github.com/Zorrorulz/MultiAgentDDPG-Tennis"},{"title":"biemann/Collaboration-and-Competition","url":"https://github.com/biemann/Collaboration-and-Competition"},{"title":"hepengli/multiagent-particle-envs","url":"https://github.com/hepengli/multiagent-particle-envs"},{"title":"jiayu-ch15/MPE-for-curriculum-learning","url":"https://github.com/jiayu-ch15/MPE-for-curriculum-learning"},{"title":"marwanihab/RL_Testing_Noise_ASRN","url":"https://github.com/marwanihab/RL_Testing_Noise_ASRN"},{"title":"AleXander-Tsui/MPE","url":"https://github.com/AleXander-Tsui/MPE"},{"title":"madhur-tandon/RL-Project","url":"https://github.com/madhur-tandon/RL-Project"},{"title":"rainandwind1/MADDPG-reconstruct","url":"https://github.com/rainandwind1/MADDPG-reconstruct"},{"title":"RL-WFU/multi_agent_attack","url":"https://github.com/RL-WFU/multi_agent_attack"},{"title":"JinTanda/MADDPG_env","url":"https://github.com/JinTanda/MADDPG_env"},{"title":"jansenkeith501/CS295-MADDPG","url":"https://github.com/jansenkeith501/CS295-MADDPG"},{"title":"baradist/multiagent-particle-envs","url":"https://github.com/baradist/multiagent-particle-envs"},{"title":"krasing/DRLearningCollaboration","url":"https://github.com/krasing/DRLearningCollaboration"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":9,"of":9,"counts":{"papers_with_a_benchmark_row":9,"with_a_code_link":8,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":9,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/the-starcraft-multi-agent-challenges-learning","slug":"the-starcraft-multi-agent-challenges-learning","title":"The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions","date":"2022-07-05","arxiv_id":"2207.02007","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/disentangling-sources-of-risk-for","slug":"disentangling-sources-of-risk-for","title":"Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/decomposed-soft-actor-critic-method-for","slug":"decomposed-soft-actor-critic-method-for","title":"Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning","date":"2021-04-14","arxiv_id":"2104.06655","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dfac-framework-factorizing-the-value-function","slug":"dfac-framework-factorizing-the-value-function","title":"DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning","date":"2021-02-16","arxiv_id":"2102.07936","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["j3soon/dfac"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dfac-framework-factorizing-the-value-function#ran","syntology_url":"https://syntology.ai/paper/2102.07936","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07936"}}}},{"paper":"/paper/qtran-learning-to-factorize-with","slug":"qtran-learning-to-factorize-with","title":"QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning","date":"2019-05-14","arxiv_id":"1905.05408","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["Sonkyunghwan/QTRAN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qtran-learning-to-factorize-with#ran","syntology_url":"https://syntology.ai/paper/1905.05408","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05408"}}}},{"paper":"/paper/qmix-monotonic-value-function-factorisation","slug":"qmix-monotonic-value-function-factorisation","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","date":"2018-03-30","arxiv_id":"1803.11485","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":7,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":6,"official":{"repos":["oxwhirl/pymarl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qmix-monotonic-value-function-factorisation#ran","syntology_url":"https://syntology.ai/paper/1803.11485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.11485"}}}},{"paper":"/paper/value-decomposition-networks-for-cooperative","slug":"value-decomposition-networks-for-cooperative","title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","date":"2017-06-16","arxiv_id":"1706.05296","rows_on_this_dataset":1,"code_links":10,"syntology":null},{"paper":"/paper/multi-agent-actor-critic-for-mixed","slug":"multi-agent-actor-critic-for-mixed","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","date":"2017-06-07","arxiv_id":"1706.02275","rows_on_this_dataset":1,"code_links":86,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":143,"samples_ran":75,"samples_constructed":54,"samples_ran_checked":68,"samples_ran_instrument_failed":7,"samples_unverified":68,"pointer_only_for_licence":99,"official":{"repos":["openai/multiagent-particle-envs"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-agent-actor-critic-for-mixed#ran","syntology_url":"https://syntology.ai/paper/1706.02275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.02275"}}}},{"paper":"/paper/counterfactual-multi-agent-policy-gradients","slug":"counterfactual-multi-agent-policy-gradients","title":"Counterfactual Multi-Agent Policy Gradients","date":"2017-05-24","arxiv_id":"1705.08926","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/counterfactual-multi-agent-policy-gradients#ran","syntology_url":"https://syntology.ai/paper/1705.08926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.08926"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/the-starcraft-multi-agent-challenges-learning","slug":"the-starcraft-multi-agent-challenges-learning","title":"The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions","date":"2022-07-05","arxiv_id":"2207.02007","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/disentangling-sources-of-risk-for","slug":"disentangling-sources-of-risk-for","title":"Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/decomposed-soft-actor-critic-method-for","slug":"decomposed-soft-actor-critic-method-for","title":"Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning","date":"2021-04-14","arxiv_id":"2104.06655","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dfac-framework-factorizing-the-value-function","slug":"dfac-framework-factorizing-the-value-function","title":"DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning","date":"2021-02-16","arxiv_id":"2102.07936","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["j3soon/dfac"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dfac-framework-factorizing-the-value-function#ran","syntology_url":"https://syntology.ai/paper/2102.07936","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07936"}}}},{"paper":"/paper/qtran-learning-to-factorize-with","slug":"qtran-learning-to-factorize-with","title":"QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning","date":"2019-05-14","arxiv_id":"1905.05408","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["Sonkyunghwan/QTRAN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qtran-learning-to-factorize-with#ran","syntology_url":"https://syntology.ai/paper/1905.05408","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05408"}}}},{"paper":"/paper/qmix-monotonic-value-function-factorisation","slug":"qmix-monotonic-value-function-factorisation","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","date":"2018-03-30","arxiv_id":"1803.11485","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":7,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":6,"official":{"repos":["oxwhirl/pymarl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qmix-monotonic-value-function-factorisation#ran","syntology_url":"https://syntology.ai/paper/1803.11485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.11485"}}}},{"paper":"/paper/value-decomposition-networks-for-cooperative","slug":"value-decomposition-networks-for-cooperative","title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","date":"2017-06-16","arxiv_id":"1706.05296","rows_on_this_dataset":1,"code_links":10,"syntology":null},{"paper":"/paper/multi-agent-actor-critic-for-mixed","slug":"multi-agent-actor-critic-for-mixed","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","date":"2017-06-07","arxiv_id":"1706.02275","rows_on_this_dataset":1,"code_links":86,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":143,"samples_ran":75,"samples_constructed":54,"samples_ran_checked":68,"samples_ran_instrument_failed":7,"samples_unverified":68,"pointer_only_for_licence":99,"official":{"repos":["openai/multiagent-particle-envs"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-agent-actor-critic-for-mixed#ran","syntology_url":"https://syntology.ai/paper/1706.02275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.02275"}}}},{"paper":"/paper/counterfactual-multi-agent-policy-gradients","slug":"counterfactual-multi-agent-policy-gradients","title":"Counterfactual Multi-Agent Policy Gradients","date":"2017-05-24","arxiv_id":"1705.08926","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/counterfactual-multi-agent-policy-gradients#ran","syntology_url":"https://syntology.ai/paper/1705.08926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.08926"}}}}],"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/dataset/smac-def-infantry-sequential/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/smac-def-infantry-sequential/papers/ran/1","json":"/dataset/smac-def-infantry-sequential/papers/ran/1.json","rows":4}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":5,"samples_harvested":157,"samples_ran":86,"samples_constructed":62,"samples_ran_checked":77,"samples_ran_instrument_failed":9,"samples_unverified":71,"pointer_only_for_licence":107,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":4,"papers_with_a_run_with_no_instrument_failure":3,"papers_where_every_run_was_an_instrument_failure":1,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"70817a272f5b2fdbde936e71593d41745bb33572c80198f6ea3c000877a8fb36","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}