{"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":"/task/multi-agent-reinforcement-learning","name":"Multi-agent Reinforcement Learning","slug":"multi-agent-reinforcement-learning","description_markdown":"The target of **Multi-agent Reinforcement Learning** is to solve complex problems by integrating multiple agents that focus on different sub-tasks. In general, there are two types of multi-agent systems: independent and cooperative systems.\n\n\n<span class=\"description-source\">Source: [Show, Describe and Conclude: On Exploiting the Structure Information of Chest X-Ray Reports ](https://arxiv.org/abs/2004.12274)</span>","categories":[{"name":"Methodology","url":"/area/methodology"},{"name":"Playing Games","url":"/area/playing-games"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1718,"papers_with_code":522,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":9,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/multi-agent-reinforcement-learning-on","slug":"multi-agent-reinforcement-learning-on","dataset":"ParticleEnvs Cooperative Communication","dataset_url":null,"rows_in_archive":1,"metrics":["final agent reward"],"first_row_in_archive_order":{"model":"MATD3","paper_title":"Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics","paper_url":"/paper/reducing-overestimation-bias-in-multi-agent","paper_date":"2019-10-03","arxiv_id":"1910.01465","code_links":[{"title":"JohannesAck/tf2multiagentrl","url":"https://github.com/JohannesAck/tf2multiagentrl"},{"title":"JohannesAck/MATD3implementation","url":"https://github.com/JohannesAck/MATD3implementation"},{"title":"fdcl-gwu/gym-rotor","url":"https://github.com/fdcl-gwu/gym-rotor"}],"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/reducing-overestimation-bias-in-multi-agent#ran","syntology_url":"https://syntology.ai/paper/1910.01465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.01465"}},"official":{"repos":["JohannesAck/MATD3implementation"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/multi-agent-reinforcement-learning-on-smac","slug":"multi-agent-reinforcement-learning-on-smac","dataset":"SMAC-Exp","dataset_url":"/dataset/smac-plus","rows_in_archive":1,"metrics":["Median Win Rate"],"first_row_in_archive_order":{"model":"DRIMA","paper_title":"Neural Processes with Stochastic Attention: Paying more attention to the context dataset","paper_url":"/paper/neural-processes-with-stochastic-attention-1","paper_date":"2022-04-11","arxiv_id":"2204.05449","code_links":[{"title":"mingyukim87/npwsa","url":"https://github.com/mingyukim87/npwsa"}],"syntology":null}},{"leaderboard":"/sota/multi-agent-reinforcement-learning-on-uav","slug":"multi-agent-reinforcement-learning-on-uav","dataset":"UAV Logistics","dataset_url":null,"rows_in_archive":1,"metrics":["Average Reward"],"first_row_in_archive_order":{"model":"Fusion-Multi-Actor-Attention-Critic","paper_title":"Multiagent Reinforcement Learning Based on Fusion-Multiactor-Attention-Critic for Multiple-Unmanned-Aerial-Vehicle Navigation Control","paper_url":"/paper/multiagent-reinforcement-learning-based-on","paper_date":"2022-10-10","arxiv_id":null,"code_links":[{"title":"leehe228/LogisticsEnv","url":"https://github.com/leehe228/LogisticsEnv"}],"syntology":null}}],"datasets":[{"url":"/dataset/cityflow","name":"CityFlow","full_name":"","num_papers_in_archive":47},{"url":"/dataset/starcraft-ii-learning-environment","name":"StarCraft II Learning Environment","full_name":"StarCraft II Learning Environment","num_papers_in_archive":26},{"url":"/dataset/smac-plus","name":"SMAC-Exp","full_name":"StarCraft Multi-Agent Exploration Challenge","num_papers_in_archive":11},{"url":"/dataset/hanabi-learning-environment","name":"Hanabi Learning Environment","full_name":"","num_papers_in_archive":10},{"url":"/dataset/og-marl","name":"OG-MARL","full_name":"Off-the-Grid MARL Datasets","num_papers_in_archive":6},{"url":"/dataset/civrealm","name":"CivRealm","full_name":"","num_papers_in_archive":4},{"url":"/dataset/colosseumrl","name":"ColosseumRL","full_name":"","num_papers_in_archive":1},{"url":"/dataset/pursuitmw","name":"pursuitMW","full_name":"Multi-agent pursuit in matrix world","num_papers_in_archive":1},{"url":"/dataset/roomenv","name":"RoomEnv-v0","full_name":"The Room environment - v0","num_papers_in_archive":1}],"subtasks":[{"url":"/task/smac","name":"SMAC"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":18,"rows_per_page":100,"shown":100,"of":1718,"of_with_code":522,"tagged_in_all":1718,"counts":{"archive_papers_tagged":1718,"with_a_code_link":522,"where_syntology_ran_a_sample":135,"not_listed_spam_title":0,"listed":1718,"listed_where_code_ran":135,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":117,"every_run_a_failure_of_syntologys_instrument":18,"listed_with_a_run_with_no_instrument_failure":117,"listed_every_run_a_failure_of_syntologys_instrument":18,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/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","repositories_listed":86,"syntology":{"n":143,"n_ran":75,"n_constructed":54,"n_ran_checked":68,"n_instrument":7,"n_unverified":68,"n_honours":2,"n_violates":0,"n_no_contract":66,"n_pointer_only":99,"phrase":"75 ran (of which 54 constructed an object rather than computing a result; 68 with no instrument failure: 2 honoured, 0 violated, 66 with no contract checked; 7 where Syntology's instrument failed) · 68 unverified","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"}},"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"]}}},{"url":"/paper/the-starcraft-multi-agent-challenge","slug":"the-starcraft-multi-agent-challenge","title":"The StarCraft Multi-Agent Challenge","date":"2019-02-11","arxiv_id":"1902.04043","repositories_listed":23,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":14,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/the-starcraft-multi-agent-challenge#ran","syntology_url":"https://syntology.ai/paper/1902.04043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.04043"}},"official":{"repos":["oxwhirl/pymarl","oxwhirl/smac"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/the-surprising-effectiveness-of-mappo-in","slug":"the-surprising-effectiveness-of-mappo-in","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","date":"2021-03-02","arxiv_id":"2103.01955","repositories_listed":19,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-surprising-effectiveness-of-mappo-in#ran","syntology_url":"https://syntology.ai/paper/2103.01955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.01955"}},"official":{"repos":["marlbenchmark/on-policy"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/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","repositories_listed":18,"syntology":{"n":11,"n_ran":9,"n_constructed":7,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":6,"phrase":"9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"url":"/paper/trust-region-policy-optimisation-in-multi","slug":"trust-region-policy-optimisation-in-multi","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","date":"2021-09-23","arxiv_id":"2109.11251","repositories_listed":11,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/trust-region-policy-optimisation-in-multi#ran","syntology_url":"https://syntology.ai/paper/2109.11251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.11251"}},"official":{"repos":["cyanrain7/trust-region-policy-optimisation-in-multi-agent-reinforcement-learning","anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/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","repositories_listed":10,"syntology":null},{"url":"/paper/rlcard-a-toolkit-for-reinforcement-learning","slug":"rlcard-a-toolkit-for-reinforcement-learning","title":"RLCard: A Toolkit for Reinforcement Learning in Card Games","date":"2019-10-10","arxiv_id":"1910.04376","repositories_listed":9,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/rlcard-a-toolkit-for-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1910.04376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.04376"}},"official":{"repos":["datamllab/rlcard"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/is-independent-learning-all-you-need-in-the","slug":"is-independent-learning-all-you-need-in-the","title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","date":"2020-11-18","arxiv_id":"2011.09533","repositories_listed":7,"syntology":null},{"url":"/paper/qplex-duplex-dueling-multi-agent-q-learning","slug":"qplex-duplex-dueling-multi-agent-q-learning","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","date":"2020-08-03","arxiv_id":"2008.01062","repositories_listed":6,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/qplex-duplex-dueling-multi-agent-q-learning#ran","syntology_url":"https://syntology.ai/paper/2008.01062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.01062"}},"official":{"repos":["wjh720/QPLEX"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/learning-with-opponent-learning-awareness","slug":"learning-with-opponent-learning-awareness","title":"Learning with Opponent-Learning Awareness","date":"2017-09-13","arxiv_id":"1709.04326","repositories_listed":6,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-with-opponent-learning-awareness#ran","syntology_url":"https://syntology.ai/paper/1709.04326","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.04326"}},"official":{"repos":["alshedivat/lola"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/smarts-scalable-multi-agent-reinforcement","slug":"smarts-scalable-multi-agent-reinforcement","title":"SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving","date":"2020-10-19","arxiv_id":"2010.09776","repositories_listed":5,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/smarts-scalable-multi-agent-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2010.09776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.09776"}},"official":{"repos":["huawei-noah/SMARTS"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/fully-decentralized-multi-agent-reinforcement","slug":"fully-decentralized-multi-agent-reinforcement","title":"Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents","date":"2018-02-23","arxiv_id":"1802.08757","repositories_listed":5,"syntology":null},{"url":"/paper/stabilising-experience-replay-for-deep-multi","slug":"stabilising-experience-replay-for-deep-multi","title":"Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning","date":"2017-02-28","arxiv_id":"1702.08887","repositories_listed":5,"syntology":null},{"url":"/paper/sigmarl-a-sample-efficient-and-generalizable","slug":"sigmarl-a-sample-efficient-and-generalizable","title":"SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning","date":"2024-08-14","arxiv_id":"2408.07644","repositories_listed":4,"syntology":null},{"url":"/paper/decom-decomposed-policy-for-constrained","slug":"decom-decomposed-policy-for-constrained","title":"DeCOM: Decomposed Policy for Constrained Cooperative Multi-Agent Reinforcement Learning","date":"2021-11-10","arxiv_id":"2111.05670","repositories_listed":4,"syntology":null},{"url":"/paper/multi-agent-constrained-policy-optimisation","slug":"multi-agent-constrained-policy-optimisation","title":"Multi-Agent Constrained Policy Optimisation","date":"2021-10-06","arxiv_id":"2110.02793","repositories_listed":4,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multi-agent-constrained-policy-optimisation#ran","syntology_url":"https://syntology.ai/paper/2110.02793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02793"}},"official":{"repos":["chauncygu/multi-agent-constrained-policy-optimisation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/sample-factory-egocentric-3d-control-from","slug":"sample-factory-egocentric-3d-control-from","title":"Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning","date":"2020-06-21","arxiv_id":"2006.11751","repositories_listed":4,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sample-factory-egocentric-3d-control-from#ran","syntology_url":"https://syntology.ai/paper/2006.11751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11751"}},"official":{"repos":["alex-petrenko/sample-factory"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/weighted-qmix-expanding-monotonic-value","slug":"weighted-qmix-expanding-monotonic-value","title":"Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","date":"2020-06-18","arxiv_id":"2006.10800","repositories_listed":4,"syntology":null},{"url":"/paper/191202288","slug":"191202288","title":"Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning","date":"2019-12-04","arxiv_id":"1912.02288","repositories_listed":4,"syntology":null},{"url":"/paper/maven-multi-agent-variational-exploration","slug":"maven-multi-agent-variational-exploration","title":"MAVEN: Multi-Agent Variational Exploration","date":"2019-10-16","arxiv_id":"1910.07483","repositories_listed":4,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/maven-multi-agent-variational-exploration#ran","syntology_url":"https://syntology.ai/paper/1910.07483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.07483"}},"official":{"repos":["AnujMahajanOxf/MAVEN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/learning-transferable-cooperative-behavior-in","slug":"learning-transferable-cooperative-behavior-in","title":"Learning Transferable Cooperative Behavior in Multi-Agent Teams","date":"2019-06-04","arxiv_id":"1906.01202","repositories_listed":4,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-transferable-cooperative-behavior-in#ran","syntology_url":"https://syntology.ai/paper/1906.01202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.01202"}},"official":{"repos":["sumitsk/matrl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":4,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","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"}},"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":[]}}},{"url":"/paper/colight-learning-network-level-cooperation","slug":"colight-learning-network-level-cooperation","title":"CoLight: Learning Network-level Cooperation for Traffic Signal Control","date":"2019-05-11","arxiv_id":"1905.05717","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/colight-learning-network-level-cooperation#ran","syntology_url":"https://syntology.ai/paper/1905.05717","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05717"}},"official":{"repos":["wingsweihua/colight"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-multi-agent-reinforcement-learning-model-of","slug":"a-multi-agent-reinforcement-learning-model-of","title":"A multi-agent reinforcement learning model of common-pool resource appropriation","date":"2017-07-20","arxiv_id":"1707.06600","repositories_listed":4,"syntology":null},{"url":"/paper/multi-agent-reinforcement-learning-in","slug":"multi-agent-reinforcement-learning-in","title":"Multi-agent Reinforcement Learning in Sequential Social Dilemmas","date":"2017-02-10","arxiv_id":"1702.03037","repositories_listed":4,"syntology":null},{"url":"/paper/jaxmarl-multi-agent-rl-environments-in-jax","slug":"jaxmarl-multi-agent-rl-environments-in-jax","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","date":"2023-11-16","arxiv_id":"2311.10090","repositories_listed":3,"syntology":{"n":23,"n_ran":22,"n_constructed":0,"n_ran_checked":22,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":22,"n_pointer_only":0,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 0 honoured, 0 violated, 22 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/jaxmarl-multi-agent-rl-environments-in-jax#ran","syntology_url":"https://syntology.ai/paper/2311.10090","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.10090"}},"official":{"repos":["flairox/jaxmarl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/deep-reinforcement-learning-for-multi-agent-2","slug":"deep-reinforcement-learning-for-multi-agent-2","title":"Deep Reinforcement Learning for Multi-Agent Interaction","date":"2022-08-02","arxiv_id":"2208.01769","repositories_listed":3,"syntology":null},{"url":"/paper/the-shapley-value-in-machine-learning","slug":"the-shapley-value-in-machine-learning","title":"The Shapley Value in Machine Learning","date":"2022-02-11","arxiv_id":"2202.05594","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-shapley-value-in-machine-learning#ran","syntology_url":"https://syntology.ai/paper/2202.05594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.05594"}},"official":{"repos":["benedekrozemberczki/shapley"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/warpdrive-extremely-fast-end-to-end-deep","slug":"warpdrive-extremely-fast-end-to-end-deep","title":"WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU","date":"2021-08-31","arxiv_id":"2108.13976","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/warpdrive-extremely-fast-end-to-end-deep#ran","syntology_url":"https://syntology.ai/paper/2108.13976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.13976"}},"official":{"repos":["salesforce/warp-drive"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/learning-to-fly-a-gym-environment-with","slug":"learning-to-fly-a-gym-environment-with","title":"Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control","date":"2021-03-03","arxiv_id":"2103.02142","repositories_listed":3,"syntology":null},{"url":"/paper/meta-variationally-intrinsic-motivated","slug":"meta-variationally-intrinsic-motivated","title":"MetaVIM: Meta Variationally Intrinsic Motivated Reinforcement Learning for Decentralized Traffic Signal Control","date":"2021-01-04","arxiv_id":"2101.00746","repositories_listed":3,"syntology":null},{"url":"/paper/learning-fair-policies-in-decentralized","slug":"learning-fair-policies-in-decentralized","title":"Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning","date":"2020-12-17","arxiv_id":"2012.09421","repositories_listed":3,"syntology":null},{"url":"/paper/shared-experience-actor-critic-for-multi","slug":"shared-experience-actor-critic-for-multi","title":"Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning","date":"2020-06-12","arxiv_id":"2006.07169","repositories_listed":3,"syntology":null},{"url":"/paper/deep-multi-agent-reinforcement-learning-for","slug":"deep-multi-agent-reinforcement-learning-for","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients","date":"2020-03-14","arxiv_id":"2003.06709","repositories_listed":3,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deep-multi-agent-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2003.06709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.06709"}},"official":{"repos":["schroederdewitt/multiagent_mujoco"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/reducing-overestimation-bias-in-multi-agent","slug":"reducing-overestimation-bias-in-multi-agent","title":"Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics","date":"2019-10-03","arxiv_id":"1910.01465","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/reducing-overestimation-bias-in-multi-agent#ran","syntology_url":"https://syntology.ai/paper/1910.01465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.01465"}},"official":{"repos":["JohannesAck/MATD3implementation"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/hierarchical-critics-assignment-for-multi","slug":"hierarchical-critics-assignment-for-multi","title":"Reinforcement Learning from Hierarchical Critics","date":"2019-02-08","arxiv_id":"1902.03079","repositories_listed":3,"syntology":null},{"url":"/paper/social-influence-as-intrinsic-motivation-for","slug":"social-influence-as-intrinsic-motivation-for","title":"Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning","date":"2018-10-19","arxiv_id":"1810.08647","repositories_listed":3,"syntology":null},{"url":"/paper/actor-attention-critic-for-multi-agent","slug":"actor-attention-critic-for-multi-agent","title":"Actor-Attention-Critic for Multi-Agent Reinforcement Learning","date":"2018-10-05","arxiv_id":"1810.02912","repositories_listed":3,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/actor-attention-critic-for-multi-agent#ran","syntology_url":"https://syntology.ai/paper/1810.02912","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.02912"}},"official":{"repos":["shariqiqbal2810/MAAC"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/inequity-aversion-improves-cooperation-in","slug":"inequity-aversion-improves-cooperation-in","title":"Inequity aversion improves cooperation in intertemporal social dilemmas","date":"2018-03-23","arxiv_id":"1803.08884","repositories_listed":3,"syntology":null},{"url":"/paper/mean-field-multi-agent-reinforcement-learning","slug":"mean-field-multi-agent-reinforcement-learning","title":"Mean Field Multi-Agent Reinforcement Learning","date":"2018-02-15","arxiv_id":"1802.05438","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mean-field-multi-agent-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1802.05438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.05438"}},"official":{"repos":["mlii/mfrl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/magent-a-many-agent-reinforcement-learning","slug":"magent-a-many-agent-reinforcement-learning","title":"MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence","date":"2017-12-02","arxiv_id":"1712.00600","repositories_listed":3,"syntology":null},{"url":"/paper/learning-to-communicate-with-deep-multi-agent","slug":"learning-to-communicate-with-deep-multi-agent","title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","date":"2016-05-21","arxiv_id":"1605.06676","repositories_listed":3,"syntology":null},{"url":"/paper/novelty-guided-data-reuse-for-efficient-and","slug":"novelty-guided-data-reuse-for-efficient-and","title":"Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning","date":"2024-12-20","arxiv_id":"2412.15517","repositories_listed":2,"syntology":null},{"url":"/paper/multi-agent-reinforcement-learning-for-22","slug":"multi-agent-reinforcement-learning-for-22","title":"Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey","date":"2024-08-19","arxiv_id":"2408.09675","repositories_listed":2,"syntology":null},{"url":"/paper/tactics2d-a-multi-agent-reinforcement","slug":"tactics2d-a-multi-agent-reinforcement","title":"Tactics2D: A Highly Modular and Extensible Simulator for Driving Decision-making","date":"2023-11-18","arxiv_id":"2311.11058","repositories_listed":2,"syntology":null},{"url":"/paper/quantifying-zero-shot-coordination-capability","slug":"quantifying-zero-shot-coordination-capability","title":"ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination","date":"2023-10-08","arxiv_id":"2310.05208","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/quantifying-zero-shot-coordination-capability#ran","syntology_url":"https://syntology.ai/paper/2310.05208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05208"}},"official":{"repos":["HumanCompatibleAI/overcooked_ai","sjtu-marl/zsc-eval"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-multi-agent-reinforcement","slug":"hierarchical-multi-agent-reinforcement","title":"Hierarchical Multi-Agent Reinforcement Learning for Air Combat Maneuvering","date":"2023-09-20","arxiv_id":"2309.11247","repositories_listed":2,"syntology":null},{"url":"/paper/off-the-grid-marl-a-framework-for-dataset","slug":"off-the-grid-marl-a-framework-for-dataset","title":"Off-the-Grid MARL: Datasets with Baselines for Offline Multi-Agent Reinforcement Learning","date":"2023-02-01","arxiv_id":"2302.00521","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/off-the-grid-marl-a-framework-for-dataset#ran","syntology_url":"https://syntology.ai/paper/2302.00521","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00521"}},"official":{"repos":["instadeepai/og-marl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/modeling-moral-choices-in-social-dilemmas","slug":"modeling-moral-choices-in-social-dilemmas","title":"Modeling Moral Choices in Social Dilemmas with Multi-Agent Reinforcement Learning","date":"2023-01-20","arxiv_id":"2301.08491","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/modeling-moral-choices-in-social-dilemmas#ran","syntology_url":"https://syntology.ai/paper/2301.08491","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.08491"}},"official":{"repos":["liza-tennant/moral_choice_dyadic","Liza-Tennant/modeling_moral_choice_dyadic"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/heterogeneous-multi-robot-reinforcement","slug":"heterogeneous-multi-robot-reinforcement","title":"Heterogeneous Multi-Robot Reinforcement Learning","date":"2023-01-17","arxiv_id":"2301.07137","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/heterogeneous-multi-robot-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2301.07137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.07137"}},"official":{"repos":["proroklab/hetgppo","proroklab/vectorizedmultiagentsimulator"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-control-and-coordinate-hybrid","slug":"learning-to-control-and-coordinate-hybrid","title":"Learning to Control and Coordinate Mixed Traffic Through Robot Vehicles at Complex and Unsignalized Intersections","date":"2023-01-12","arxiv_id":"2301.05294","repositories_listed":2,"syntology":null},{"url":"/paper/asynchronous-multi-agent-reinforcement","slug":"asynchronous-multi-agent-reinforcement","title":"Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Exploration","date":"2023-01-09","arxiv_id":"2301.03398","repositories_listed":2,"syntology":null},{"url":"/paper/scalable-multi-agent-reinforcement-learning-2","slug":"scalable-multi-agent-reinforcement-learning-2","title":"Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation","date":"2022-11-03","arxiv_id":"2211.02127","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scalable-multi-agent-reinforcement-learning-2#ran","syntology_url":"https://syntology.ai/paper/2211.02127","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.02127"}},"official":{"repos":["nsidn98/informarl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/stateful-active-facilitator-coordination-and","slug":"stateful-active-facilitator-coordination-and","title":"Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning","date":"2022-10-04","arxiv_id":"2210.03022","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/stateful-active-facilitator-coordination-and#ran","syntology_url":"https://syntology.ai/paper/2210.03022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03022"}},"official":{"repos":["jaggbow/saf","veds12/hecogrid"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ai-for-global-climate-cooperation-modeling","slug":"ai-for-global-climate-cooperation-modeling","title":"AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N","date":"2022-08-15","arxiv_id":"2208.07004","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-share-in-multi-agent-1","slug":"learning-to-share-in-multi-agent-1","title":"Learning to Share in Multi-Agent Reinforcement Learning","date":"2021-12-16","arxiv_id":"2112.08702","repositories_listed":2,"syntology":null},{"url":"/paper/episodic-multi-agent-reinforcement-learning-1","slug":"episodic-multi-agent-reinforcement-learning-1","title":"Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration","date":"2021-11-22","arxiv_id":"2111.11032","repositories_listed":2,"syntology":null},{"url":"/paper/collaborating-with-humans-without-human-data","slug":"collaborating-with-humans-without-human-data","title":"Collaborating with Humans without Human Data","date":"2021-10-15","arxiv_id":"2110.08176","repositories_listed":2,"syntology":null},{"url":"/paper/metadrive-composing-diverse-driving-scenarios","slug":"metadrive-composing-diverse-driving-scenarios","title":"MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning","date":"2021-09-26","arxiv_id":"2109.12674","repositories_listed":2,"syntology":null},{"url":"/paper/celebrating-diversity-in-shared-multi-agent","slug":"celebrating-diversity-in-shared-multi-agent","title":"Celebrating Diversity in Shared Multi-Agent Reinforcement Learning","date":"2021-06-04","arxiv_id":"2106.02195","repositories_listed":2,"syntology":null},{"url":"/paper/patch-autoaugment","slug":"patch-autoaugment","title":"Local Patch AutoAugment with Multi-Agent Collaboration","date":"2021-03-20","arxiv_id":"2103.11099","repositories_listed":2,"syntology":null},{"url":"/paper/multi-agent-reinforcement-learning-in-2","slug":"multi-agent-reinforcement-learning-in-2","title":"Multi-agent Reinforcement Learning in OpenSpiel: A Reproduction Report","date":"2021-02-27","arxiv_id":"2103.00187","repositories_listed":2,"syntology":null},{"url":"/paper/hyperparameter-tricks-in-multi-agent","slug":"hyperparameter-tricks-in-multi-agent","title":"Rethinking the Implementation Matters in Cooperative Multi-Agent Reinforcement Learning","date":"2021-02-06","arxiv_id":"2102.03479","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hyperparameter-tricks-in-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2102.03479","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.03479"}},"official":{"repos":["hijkzzz/pymarl2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/solving-common-payoff-games-with-approximate","slug":"solving-common-payoff-games-with-approximate","title":"Solving Common-Payoff Games with Approximate Policy Iteration","date":"2021-01-11","arxiv_id":"2101.04237","repositories_listed":2,"syntology":{"n":9,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/solving-common-payoff-games-with-approximate#ran","syntology_url":"https://syntology.ai/paper/2101.04237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.04237"}},"official":{"repos":["ssokota/capi","ssokota/tiny-hanabi"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-agent-collaboration-via-reward-1","slug":"multi-agent-collaboration-via-reward-1","title":"Multi-Agent Collaboration via Reward Attribution Decomposition","date":"2020-10-16","arxiv_id":"2010.08531","repositories_listed":2,"syntology":null},{"url":"/paper/pettingzoo-gym-for-multi-agent-reinforcement","slug":"pettingzoo-gym-for-multi-agent-reinforcement","title":"PettingZoo: Gym for Multi-Agent Reinforcement Learning","date":"2020-09-30","arxiv_id":"2009.14471","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pettingzoo-gym-for-multi-agent-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2009.14471","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.14471"}},"official":{"repos":["Farama-Foundation/PettingZoo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reward-machines-for-cooperative-multi-agent","slug":"reward-machines-for-cooperative-multi-agent","title":"Reward Machines for Cooperative Multi-Agent Reinforcement Learning","date":"2020-07-03","arxiv_id":"2007.01962","repositories_listed":2,"syntology":null},{"url":"/paper/the-emergence-of-individuality-in-multi-agent","slug":"the-emergence-of-individuality-in-multi-agent","title":"The Emergence of Individuality","date":"2020-06-10","arxiv_id":"2006.05842","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-emergence-of-individuality-in-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2006.05842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.05842"}},"official":{"repos":["jiechuanjiang/eoi_on_smac","jiechuanjiang/eoi_pymarl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ai-qmix-attention-and-imagination-for-dynamic","slug":"ai-qmix-attention-and-imagination-for-dynamic","title":"Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning","date":"2020-06-07","arxiv_id":"2006.04222","repositories_listed":2,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/ai-qmix-attention-and-imagination-for-dynamic#ran","syntology_url":"https://syntology.ai/paper/2006.04222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04222"}},"official":{"repos":["shariqiqbal2810/REFIL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/a-deep-multi-agent-reinforcement-learning","slug":"a-deep-multi-agent-reinforcement-learning","title":"A Deep Multi-Agent Reinforcement Learning Approach to Autonomous Separation Assurance","date":"2020-03-17","arxiv_id":"2003.08353","repositories_listed":2,"syntology":null},{"url":"/paper/other-play-for-zero-shot-coordination","slug":"other-play-for-zero-shot-coordination","title":"\"Other-Play\" for Zero-Shot Coordination","date":"2020-03-06","arxiv_id":"2003.02979","repositories_listed":2,"syntology":null},{"url":"/paper/silly-rules-improve-the-capacity-of-agents-to","slug":"silly-rules-improve-the-capacity-of-agents-to","title":"Silly rules improve the capacity of agents to learn stable enforcement and compliance behaviors","date":"2020-01-25","arxiv_id":"2001.09318","repositories_listed":2,"syntology":null},{"url":"/paper/represented-value-function-approach-for-large","slug":"represented-value-function-approach-for-large","title":"Represented Value Function Approach for Large Scale Multi Agent Reinforcement Learning","date":"2020-01-04","arxiv_id":"2001.01096","repositories_listed":2,"syntology":null},{"url":"/paper/pic-permutation-invariant-critic-for-multi","slug":"pic-permutation-invariant-critic-for-multi","title":"PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement Learning","date":"2019-10-31","arxiv_id":"1911.00025","repositories_listed":2,"syntology":null},{"url":"/paper/deep-coordination-graphs","slug":"deep-coordination-graphs","title":"Deep Coordination Graphs","date":"2019-09-27","arxiv_id":"1910.00091","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-communication-in-multi-agent","slug":"efficient-communication-in-multi-agent","title":"Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control","date":"2019-09-06","arxiv_id":"1909.02682","repositories_listed":2,"syntology":null},{"url":"/paper/arena-a-toolkit-for-multi-agent-reinforcement","slug":"arena-a-toolkit-for-multi-agent-reinforcement","title":"Arena: a toolkit for Multi-Agent Reinforcement Learning","date":"2019-07-20","arxiv_id":"1907.09467","repositories_listed":2,"syntology":null},{"url":"/paper/rethink-global-reward-game-and-credit","slug":"rethink-global-reward-game-and-credit","title":"Shapley Q-value: A Local Reward Approach to Solve Global Reward Games","date":"2019-07-11","arxiv_id":"1907.05707","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/rethink-global-reward-game-and-credit#ran","syntology_url":"https://syntology.ai/paper/1907.05707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.05707"}},"official":{"repos":["hsvgbkhgbv/SQDDPG"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/arena-a-general-evaluation-platform-and","slug":"arena-a-general-evaluation-platform-and","title":"Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence","date":"2019-05-17","arxiv_id":"1905.08085","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/arena-a-general-evaluation-platform-and#ran","syntology_url":"https://syntology.ai/paper/1905.08085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.08085"}},"official":{"repos":["YuhangSong/Arena-Baselines","YuhangSong/Arena-BuildingToolkit"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/the-multi-agent-reinforcement-learning-in","slug":"the-multi-agent-reinforcement-learning-in","title":"The Multi-Agent Reinforcement Learning in MalmÖ (MARLÖ) Competition","date":"2019-01-23","arxiv_id":"1901.08129","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-multi-agent-reinforcement-learning-in#ran","syntology_url":"https://syntology.ai/paper/1901.08129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08129"}},"official":null}},{"url":"/paper/one-step-is-enough-multi-agent-reinforcement","slug":"one-step-is-enough-multi-agent-reinforcement","title":"One Step is Enough: Multi-Agent Reinforcement Learning based on One-Step Policy Optimization for Order Dispatch on Ride-Sharing Platforms","date":"2025-07-21","arxiv_id":"2507.15351","repositories_listed":1,"syntology":null},{"url":"/paper/spiral-self-play-on-zero-sum-games","slug":"spiral-self-play-on-zero-sum-games","title":"SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning","date":"2025-06-30","arxiv_id":"2506.24119","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":3,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/spiral-self-play-on-zero-sum-games#ran","syntology_url":"https://syntology.ai/paper/2506.24119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.24119"}},"official":{"repos":["spiral-rl/spiral"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-decrypto-benchmark-for-multi-agent","slug":"the-decrypto-benchmark-for-multi-agent","title":"The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind","date":"2025-06-25","arxiv_id":"2506.20664","repositories_listed":1,"syntology":null},{"url":"/paper/transformer-world-model-for-sample-efficient","slug":"transformer-world-model-for-sample-efficient","title":"Transformer World Model for Sample Efficient Multi-Agent Reinforcement Learning","date":"2025-06-23","arxiv_id":"2506.18537","repositories_listed":1,"syntology":null},{"url":"/paper/generalizable-agent-modeling-for-agent","slug":"generalizable-agent-modeling-for-agent","title":"Generalizable Agent Modeling for Agent Collaboration-Competition Adaptation with Multi-Retrieval and Dynamic Generation","date":"2025-06-20","arxiv_id":"2506.16718","repositories_listed":1,"syntology":null},{"url":"/paper/light-aircraft-game-basic-implementation-and","slug":"light-aircraft-game-basic-implementation-and","title":"Light Aircraft Game : Basic Implementation and training results analysis","date":"2025-06-17","arxiv_id":"2506.14164","repositories_listed":1,"syntology":null},{"url":"/paper/chasing-moving-targets-with-online-self-play","slug":"chasing-moving-targets-with-online-self-play","title":"Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models","date":"2025-06-09","arxiv_id":"2506.07468","repositories_listed":1,"syntology":{"n":17,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":11,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/chasing-moving-targets-with-online-self-play#ran","syntology_url":"https://syntology.ai/paper/2506.07468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.07468"}},"official":{"repos":["mickelliu/selfplay-redteaming"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":11,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/curriculum-learning-with-counterfactual-group","slug":"curriculum-learning-with-counterfactual-group","title":"Curriculum Learning With Counterfactual Group Relative Policy Advantage For Multi-Agent Reinforcement Learning","date":"2025-06-09","arxiv_id":"2506.07548","repositories_listed":1,"syntology":null},{"url":"/paper/biological-pathway-guided-gene-selection","slug":"biological-pathway-guided-gene-selection","title":"Biological Pathway Guided Gene Selection Through Collaborative Reinforcement Learning","date":"2025-05-30","arxiv_id":"2505.24155","repositories_listed":1,"syntology":null},{"url":"/paper/sorrel-a-simple-and-flexible-framework-for","slug":"sorrel-a-simple-and-flexible-framework-for","title":"Sorrel: A simple and flexible framework for multi-agent reinforcement learning","date":"2025-05-30","arxiv_id":"2506.00228","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-multi-agent-world-modeling-from-a","slug":"revisiting-multi-agent-world-modeling-from-a","title":"Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective","date":"2025-05-27","arxiv_id":"2505.20922","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-reinforcement-learning-vs-fixed","slug":"multi-agent-reinforcement-learning-vs-fixed","title":"Smart Traffic Signals: Comparing MARL and Fixed-Time Strategies","date":"2025-05-20","arxiv_id":"2505.14544","repositories_listed":1,"syntology":null},{"url":"/paper/jaxrobotarium-training-and-deploying-multi","slug":"jaxrobotarium-training-and-deploying-multi","title":"JaxRobotarium: Training and Deploying Multi-Robot Policies in 10 Minutes","date":"2025-05-10","arxiv_id":"2505.06771","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-cooperative-multi-agent","slug":"enhancing-cooperative-multi-agent","title":"Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration","date":"2025-05-08","arxiv_id":"2505.05262","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":3,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":4,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/enhancing-cooperative-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2505.05262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.05262"}},"official":{"repos":["ddaedalus/smpe"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/adaptive-and-robust-dbscan-with-multi-agent","slug":"adaptive-and-robust-dbscan-with-multi-agent","title":"Adaptive and Robust DBSCAN with Multi-agent Reinforcement Learning","date":"2025-05-07","arxiv_id":"2505.04339","repositories_listed":1,"syntology":null},{"url":"/paper/interpretable-emergent-language-using-inter","slug":"interpretable-emergent-language-using-inter","title":"Interpretable Emergent Language Using Inter-Agent Transformers","date":"2025-05-04","arxiv_id":"2505.02215","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-reinforcement-learning-for-27","slug":"multi-agent-reinforcement-learning-for-27","title":"Multi-Agent Reinforcement Learning for Resources Allocation Optimization: A Survey","date":"2025-04-29","arxiv_id":"2504.21048","repositories_listed":1,"syntology":null},{"url":"/paper/large-scale-mixed-traffic-and-intersection","slug":"large-scale-mixed-traffic-and-intersection","title":"Large-Scale Mixed-Traffic and Intersection Control using Multi-agent Reinforcement Learning","date":"2025-04-07","arxiv_id":"2504.04691","repositories_listed":1,"syntology":null},{"url":"/paper/a-constrained-multi-agent-reinforcement","slug":"a-constrained-multi-agent-reinforcement","title":"A Constrained Multi-Agent Reinforcement Learning Approach to Autonomous Traffic Signal Control","date":"2025-03-30","arxiv_id":"2503.23626","repositories_listed":1,"syntology":null},{"url":"/paper/an-organizationally-oriented-approach-to","slug":"an-organizationally-oriented-approach-to","title":"An Organizationally-Oriented Approach to Enhancing Explainability and Control in Multi-Agent Reinforcement Learning","date":"2025-03-30","arxiv_id":"2503.23615","repositories_listed":1,"syntology":null}],"syntology_records":39,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"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_where_code_ran":135,"papers_where_code_ran_first_page":"/task/multi-agent-reinforcement-learning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":18,"url":"/task/multi-agent-reinforcement-learning/papers/2","json":"/task/multi-agent-reinforcement-learning/papers/2.json","rows":100},{"order":"archive","page":3,"of":18,"url":"/task/multi-agent-reinforcement-learning/papers/3","json":"/task/multi-agent-reinforcement-learning/papers/3.json","rows":100},{"order":"archive","page":4,"of":18,"url":"/task/multi-agent-reinforcement-learning/papers/4","json":"/task/multi-agent-reinforcement-learning/papers/4.json","rows":100},{"order":"archive","page":5,"of":18,"url":"/task/multi-agent-reinforcement-learning/papers/5","json":"/task/multi-agent-reinforcement-learning/papers/5.json","rows":100},{"order":"archive","page":6,"of":18,"url":"/task/multi-agent-reinforcement-learning/papers/6","json":"/task/multi-agent-reinforcement-learning/papers/6.json","rows":100},{"order":"archive","page":7,"of":18,"url":"/task/multi-agent-reinforcement-learning/papers/7","json":"/task/multi-agent-reinforcement-learning/papers/7.json","rows":100},{"order":"archive","page":8,"of":18,"url":"/task/multi-agent-reinforcement-learning/papers/8","json":"/task/multi-agent-reinforcement-learning/papers/8.json","rows":100},{"order":"archive","page":9,"of":18,"url":"/task/multi-agent-reinforcement-learning/papers/9","json":"/task/multi-agent-reinforcement-learning/papers/9.json","rows":100},{"order":"archive","page":10,"of":18,"url":"/task/multi-agent-reinforcement-learning/papers/10","json":"/task/multi-agent-reinforcement-learning/papers/10.json","rows":100},{"order":"archive","page":11,"of":18,"url":"/task/multi-agent-reinforcement-learning/papers/11","json":"/task/multi-agent-reinforcement-learning/papers/11.json","rows":100},{"order":"archive","page":12,"of":18,"url":"/task/multi-agent-reinforcement-learning/papers/12","json":"/task/multi-agent-reinforcement-learning/papers/12.json","rows":100},{"order":"archive","page":13,"of":18,"url":"/task/multi-agent-reinforcement-learning/papers/13","json":"/task/multi-agent-reinforcement-learning/papers/13.json","rows":100},{"order":"archive","page":14,"of":18,"url":"/task/multi-agent-reinforcement-learning/papers/14","json":"/task/multi-agent-reinforcement-learning/papers/14.json","rows":100},{"order":"archive","page":15,"of":18,"url":"/task/multi-agent-reinforcement-learning/papers/15","json":"/task/multi-agent-reinforcement-learning/papers/15.json","rows":100},{"order":"archive","page":16,"of":18,"url":"/task/multi-agent-reinforcement-learning/papers/16","json":"/task/multi-agent-reinforcement-learning/papers/16.json","rows":100},{"order":"archive","page":17,"of":18,"url":"/task/multi-agent-reinforcement-learning/papers/17","json":"/task/multi-agent-reinforcement-learning/papers/17.json","rows":100},{"order":"archive","page":18,"of":18,"url":"/task/multi-agent-reinforcement-learning/papers/18","json":"/task/multi-agent-reinforcement-learning/papers/18.json","rows":18},{"order":"ran","page":1,"of":2,"url":"/task/multi-agent-reinforcement-learning/papers/ran/1","json":"/task/multi-agent-reinforcement-learning/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/multi-agent-reinforcement-learning/papers/ran/2","json":"/task/multi-agent-reinforcement-learning/papers/ran/2.json","rows":35}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"ab41a990dd612713ed9acd5d45141032af627b79ab8bba5f8276cd37ecfa4a8c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}