{"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/starcraft-ii","name":"Starcraft II","slug":"starcraft-ii","description_markdown":"Starcraft II is a RTS game; the task is to train an agent to play the game.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [The StarCraft Multi-Agent Challenge](https://arxiv.org/pdf/1902.04043v2.pdf) )</span>","categories":[{"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":175,"papers_with_code":90,"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":6,"subtasks":0,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/starcraft-ii-on-collectmineralshards","slug":"starcraft-ii-on-collectmineralshards","dataset":"CollectMineralShards","dataset_url":null,"rows_in_archive":1,"metrics":["Max Score"],"first_row_in_archive_order":{"model":"FullyConv LSTM","paper_title":"StarCraft II: A New Challenge for Reinforcement Learning","paper_url":"/paper/starcraft-ii-a-new-challenge-for","paper_date":"2017-08-16","arxiv_id":"1708.04782","code_links":[{"title":"deepmind/pysc2","url":"https://github.com/deepmind/pysc2"},{"title":"google-deepmind/pysc2","url":"https://github.com/google-deepmind/pysc2"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"inoryy/reaver","url":"https://github.com/inoryy/reaver"},{"title":"4rChon/NL-FuN","url":"https://github.com/4rChon/NL-FuN"},{"title":"nicoladainese96/SC2-RL","url":"https://github.com/nicoladainese96/SC2-RL"},{"title":"tuomaso/SC2LE-implementation","url":"https://github.com/tuomaso/SC2LE-implementation"},{"title":"raccoon831012/StartCraft2-RL","url":"https://github.com/raccoon831012/StartCraft2-RL"},{"title":"ericborn/binarybot","url":"https://github.com/ericborn/binarybot"},{"title":"Teslatic/SC2-Freiburg","url":"https://github.com/Teslatic/SC2-Freiburg"}],"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/starcraft-ii-a-new-challenge-for#ran","syntology_url":"https://syntology.ai/paper/1708.04782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.04782"}},"official":{"repos":["deepmind/pysc2"],"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"]}}}},{"leaderboard":"/sota/starcraft-ii-on-movetobeacon","slug":"starcraft-ii-on-movetobeacon","dataset":"MoveToBeacon","dataset_url":null,"rows_in_archive":1,"metrics":["Max Score"],"first_row_in_archive_order":{"model":"FullyConv LSTM","paper_title":"StarCraft II: A New Challenge for Reinforcement Learning","paper_url":"/paper/starcraft-ii-a-new-challenge-for","paper_date":"2017-08-16","arxiv_id":"1708.04782","code_links":[{"title":"deepmind/pysc2","url":"https://github.com/deepmind/pysc2"},{"title":"google-deepmind/pysc2","url":"https://github.com/google-deepmind/pysc2"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"inoryy/reaver","url":"https://github.com/inoryy/reaver"},{"title":"4rChon/NL-FuN","url":"https://github.com/4rChon/NL-FuN"},{"title":"nicoladainese96/SC2-RL","url":"https://github.com/nicoladainese96/SC2-RL"},{"title":"tuomaso/SC2LE-implementation","url":"https://github.com/tuomaso/SC2LE-implementation"},{"title":"raccoon831012/StartCraft2-RL","url":"https://github.com/raccoon831012/StartCraft2-RL"},{"title":"ericborn/binarybot","url":"https://github.com/ericborn/binarybot"},{"title":"Teslatic/SC2-Freiburg","url":"https://github.com/Teslatic/SC2-Freiburg"}],"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/starcraft-ii-a-new-challenge-for#ran","syntology_url":"https://syntology.ai/paper/1708.04782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.04782"}},"official":{"repos":["deepmind/pysc2"],"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"]}}}},{"leaderboard":"/sota/starcraft-ii-on-smac","slug":"starcraft-ii-on-smac","dataset":"SMAC-Exp","dataset_url":"/dataset/smac-plus","rows_in_archive":1,"metrics":["Median Win Rate"],"first_row_in_archive_order":{"model":"QMIX","paper_title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","paper_url":"/paper/qmix-monotonic-value-function-factorisation","paper_date":"2018-03-30","arxiv_id":"1803.11485","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/qmix.py"},{"title":"oxwhirl/pymarl","url":"https://github.com/oxwhirl/pymarl"},{"title":"starry-sky6688/marl-algorithms","url":"https://github.com/starry-sky6688/marl-algorithms"},{"title":"oxwhirl/smac","url":"https://github.com/oxwhirl/smac"},{"title":"facebookresearch/benchmarl","url":"https://github.com/facebookresearch/benchmarl"},{"title":"hhhusiyi-monash/UPDeT","url":"https://github.com/hhhusiyi-monash/UPDeT"},{"title":"TonghanWang/NDQ","url":"https://github.com/TonghanWang/NDQ"},{"title":"nju-rl/acorm","url":"https://github.com/nju-rl/acorm"},{"title":"TonghanWang/DOP","url":"https://github.com/TonghanWang/DOP"},{"title":"puyuan1996/MARL","url":"https://github.com/puyuan1996/MARL"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/qmix"},{"title":"cathyhxh/ctds","url":"https://github.com/cathyhxh/ctds"},{"title":"jugg1er/air","url":"https://github.com/jugg1er/air"},{"title":"ifpen/wfcrl-benchmark","url":"https://github.com/ifpen/wfcrl-benchmark"},{"title":"gingkg/smac","url":"https://github.com/gingkg/smac"},{"title":"15534081591/QMIX","url":"https://github.com/15534081591/QMIX"},{"title":"2023-MindSpore-1/ms-code-221","url":"https://github.com/2023-MindSpore-1/ms-code-221/tree/main/qmix"}],"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"]}}}}],"datasets":[{"url":"/dataset/starcraft-ii-learning-environment","name":"StarCraft II Learning Environment","full_name":"StarCraft II Learning Environment","num_papers_in_archive":26},{"url":"/dataset/lani","name":"Lani","full_name":null,"num_papers_in_archive":12},{"url":"/dataset/smac-plus","name":"SMAC-Exp","full_name":"StarCraft Multi-Agent Exploration Challenge","num_papers_in_archive":11},{"url":"/dataset/msc","name":"MSC","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/sc2egset-starcraft-ii-esport-game-state","name":"SC2EGSet: StarCraft II Esport Game State Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/sc2reset-starcraft-ii-esport-replaypack-set","name":"SC2ReSet: StarCraft II Esport Replaypack Set","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/real-time-strategy-games","name":"Real-Time Strategy Games"},{"url":"/task/video-games","name":"Video Games"}],"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":2,"rows_per_page":100,"shown":100,"of":175,"of_with_code":90,"tagged_in_all":175,"counts":{"archive_papers_tagged":175,"with_a_code_link":90,"where_syntology_ran_a_sample":22,"not_listed_spam_title":0,"listed":175,"listed_where_code_ran":22,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":18,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":18,"listed_every_run_a_failure_of_syntologys_instrument":4,"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/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/starcraft-ii-a-new-challenge-for","slug":"starcraft-ii-a-new-challenge-for","title":"StarCraft II: A New Challenge for Reinforcement Learning","date":"2017-08-16","arxiv_id":"1708.04782","repositories_listed":10,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/starcraft-ii-a-new-challenge-for#ran","syntology_url":"https://syntology.ai/paper/1708.04782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.04782"}},"official":{"repos":["deepmind/pysc2"],"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/perceiver-io-a-general-architecture-for","slug":"perceiver-io-a-general-architecture-for","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","date":"2021-07-30","arxiv_id":"2107.14795","repositories_listed":9,"syntology":{"n":11,"n_ran":7,"n_constructed":4,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/perceiver-io-a-general-architecture-for#ran","syntology_url":"https://syntology.ai/paper/2107.14795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.14795"}},"official":{"repos":["deepmind/deepmind-research"],"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/relational-deep-reinforcement-learning","slug":"relational-deep-reinforcement-learning","title":"Relational Deep Reinforcement Learning","date":"2018-06-05","arxiv_id":"1806.01830","repositories_listed":7,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"5 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; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/relational-deep-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1806.01830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.01830"}},"official":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/gym-m-rts-toward-affordable-full-game-real","slug":"gym-m-rts-toward-affordable-full-game-real","title":"Gym-$μ$RTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning","date":"2021-05-21","arxiv_id":"2105.13807","repositories_listed":5,"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-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/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/on-efficient-reinforcement-learning-for-full","slug":"on-efficient-reinforcement-learning-for-full","title":"On Efficient Reinforcement Learning for Full-length Game of StarCraft II","date":"2022-09-23","arxiv_id":"2209.11553","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/on-efficient-reinforcement-learning-for-full#ran","syntology_url":"https://syntology.ai/paper/2209.11553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.11553"}},"official":{"repos":["liuruoze/hiernet-sc2","liuruoze/mini-AlphaStar"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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/rethinking-of-alphastar","slug":"rethinking-of-alphastar","title":"Rethinking of AlphaStar","date":"2021-08-07","arxiv_id":"2108.03452","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/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/rode-learning-roles-to-decompose-multi-agent-1","slug":"rode-learning-roles-to-decompose-multi-agent-1","title":"RODE: Learning Roles to Decompose Multi-Agent Tasks","date":"2020-10-04","arxiv_id":"2010.01523","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/explainable-reinforcement-learning-through-a","slug":"explainable-reinforcement-learning-through-a","title":"Explainable Reinforcement Learning Through a Causal Lens","date":"2019-05-27","arxiv_id":"1905.10958","repositories_listed":2,"syntology":null},{"url":"/paper/tstarbots-defeating-the-cheating-level","slug":"tstarbots-defeating-the-cheating-level","title":"TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game","date":"2018-09-19","arxiv_id":"1809.07193","repositories_listed":2,"syntology":null},{"url":"/paper/msc-a-dataset-for-macro-management-in","slug":"msc-a-dataset-for-macro-management-in","title":"MSC: A Dataset for Macro-Management in StarCraft II","date":"2017-10-09","arxiv_id":"1710.03131","repositories_listed":2,"syntology":null},{"url":"/paper/vlms-play-starcraft-ii-a-benchmark-and","slug":"vlms-play-starcraft-ii-a-benchmark-and","title":"AVA: Attentive VLM Agent for Mastering StarCraft II","date":"2025-03-07","arxiv_id":"2503.05383","repositories_listed":1,"syntology":null},{"url":"/paper/trajectory-class-aware-multi-agent","slug":"trajectory-class-aware-multi-agent","title":"Trajectory-Class-Aware Multi-Agent Reinforcement Learning","date":"2025-03-03","arxiv_id":"2503.01440","repositories_listed":1,"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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/trajectory-class-aware-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2503.01440","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.01440"}},"official":{"repos":["aailab-kaist/trama"],"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/pmat-optimizing-action-generation-order-in","slug":"pmat-optimizing-action-generation-order-in","title":"PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning","date":"2025-02-23","arxiv_id":"2502.16496","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-expert-prompt-for-large-language","slug":"hierarchical-expert-prompt-for-large-language","title":"Hierarchical Expert Prompt for Large-Language-Model: An Approach Defeat Elite AI in TextStarCraft II for the First Time","date":"2025-02-16","arxiv_id":"2502.11122","repositories_listed":1,"syntology":null},{"url":"/paper/tackling-uncertainties-in-multi-agent","slug":"tackling-uncertainties-in-multi-agent","title":"Tackling Uncertainties in Multi-Agent Reinforcement Learning through Integration of Agent Termination Dynamics","date":"2025-01-21","arxiv_id":"2501.12061","repositories_listed":1,"syntology":null},{"url":"/paper/llm-pysc2-starcraft-ii-learning-environment","slug":"llm-pysc2-starcraft-ii-learning-environment","title":"LLM-PySC2: Starcraft II learning environment for Large Language Models","date":"2024-11-08","arxiv_id":"2411.05348","repositories_listed":1,"syntology":null},{"url":"/paper/carefully-structured-compression-efficiently","slug":"carefully-structured-compression-efficiently","title":"Carefully Structured Compression: Efficiently Managing StarCraft II Data","date":"2024-10-11","arxiv_id":"2410.08659","repositories_listed":1,"syntology":null},{"url":"/paper/assigning-credit-with-partial-reward","slug":"assigning-credit-with-partial-reward","title":"Assigning Credit with Partial Reward Decoupling in Multi-Agent Proximal Policy Optimization","date":"2024-08-08","arxiv_id":"2408.04295","repositories_listed":1,"syntology":null},{"url":"/paper/group-aware-coordination-graph-for-multi","slug":"group-aware-coordination-graph-for-multi","title":"Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning","date":"2024-04-17","arxiv_id":"2404.10976","repositories_listed":1,"syntology":null},{"url":"/paper/n-agent-ad-hoc-teamwork","slug":"n-agent-ad-hoc-teamwork","title":"N-Agent Ad Hoc Teamwork","date":"2024-04-16","arxiv_id":"2404.10740","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":5,"n_honours":4,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/n-agent-ad-hoc-teamwork#ran","syntology_url":"https://syntology.ai/paper/2404.10740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10740"}},"official":{"repos":["carolinewang01/naht"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/inferring-latent-temporal-sparse-coordination","slug":"inferring-latent-temporal-sparse-coordination","title":"Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning","date":"2024-03-28","arxiv_id":"2403.19253","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-episodic-memory-utilization-of","slug":"efficient-episodic-memory-utilization-of","title":"Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning","date":"2024-03-02","arxiv_id":"2403.01112","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/efficient-episodic-memory-utilization-of#ran","syntology_url":"https://syntology.ai/paper/2403.01112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01112"}},"official":{"repos":["hyunghona/emu"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/swarmbrain-embodied-agent-for-real-time","slug":"swarmbrain-embodied-agent-for-real-time","title":"SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language models","date":"2024-01-31","arxiv_id":"2401.17749","repositories_listed":1,"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":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) · 0 unverified","sample_list":"/paper/swarmbrain-embodied-agent-for-real-time#ran","syntology_url":"https://syntology.ai/paper/2401.17749","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17749"}},"official":{"repos":["ramsayxiaoshao/SwarmBrain-Embodied-agent-for-real-time-strategy-game-StarCraft-II-via-large-language-models"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-play-starcraft-ii","slug":"large-language-models-play-starcraft-ii","title":"Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach","date":"2023-12-19","arxiv_id":"2312.11865","repositories_listed":1,"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":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) · 0 unverified","sample_list":"/paper/large-language-models-play-starcraft-ii#ran","syntology_url":"https://syntology.ai/paper/2312.11865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11865"}},"official":{"repos":["histmeisah/large-language-models-play-starcraftii"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/codex-a-cluster-based-method-for-explainable","slug":"codex-a-cluster-based-method-for-explainable","title":"CODEX: A Cluster-Based Method for Explainable Reinforcement Learning","date":"2023-12-07","arxiv_id":"2312.04216","repositories_listed":1,"syntology":null},{"url":"/paper/fox-formation-aware-exploration-in-multi","slug":"fox-formation-aware-exploration-in-multi","title":"FoX: Formation-aware exploration in multi-agent reinforcement learning","date":"2023-08-22","arxiv_id":"2308.11272","repositories_listed":1,"syntology":null},{"url":"/paper/alphastar-unplugged-large-scale-offline","slug":"alphastar-unplugged-large-scale-offline","title":"AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning","date":"2023-08-07","arxiv_id":"2308.03526","repositories_listed":1,"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/alphastar-unplugged-large-scale-offline#ran","syntology_url":"https://syntology.ai/paper/2308.03526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03526"}},"official":null}},{"url":"/paper/offline-multi-agent-reinforcement-learning-1","slug":"offline-multi-agent-reinforcement-learning-1","title":"Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization","date":"2023-07-21","arxiv_id":"2307.11620","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"4 ran (of which 4 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) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/offline-multi-agent-reinforcement-learning-1#ran","syntology_url":"https://syntology.ai/paper/2307.11620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.11620"}},"official":{"repos":["zhengyinan-air/omiga"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/semantic-helm-a-human-readable-memory-for-1","slug":"semantic-helm-a-human-readable-memory-for-1","title":"Semantic HELM: A Human-Readable Memory for Reinforcement Learning","date":"2023-06-15","arxiv_id":"2306.09312","repositories_listed":1,"syntology":null},{"url":"/paper/expode-exploiting-policy-discrepancy-for","slug":"expode-exploiting-policy-discrepancy-for","title":"EXPODE: EXploiting POlicy Discrepancy for Efficient Exploration in Multi-agent Reinforcement Learning","date":"2023-05-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/is-centralized-training-with-decentralized","slug":"is-centralized-training-with-decentralized","title":"Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?","date":"2023-05-27","arxiv_id":"2305.17352","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/is-centralized-training-with-decentralized#ran","syntology_url":"https://syntology.ai/paper/2305.17352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17352"}},"official":{"repos":["zyh1999/cadp"],"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/smaclite-a-lightweight-environment-for-multi","slug":"smaclite-a-lightweight-environment-for-multi","title":"SMAClite: A Lightweight Environment for Multi-Agent Reinforcement Learning","date":"2023-05-09","arxiv_id":"2305.05566","repositories_listed":1,"syntology":null},{"url":"/paper/effective-and-stable-role-based-multi-agent","slug":"effective-and-stable-role-based-multi-agent","title":"Effective and Stable Role-Based Multi-Agent Collaboration by Structural Information Principles","date":"2023-04-03","arxiv_id":"2304.00755","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":4,"n_ran_checked":5,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":11,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/effective-and-stable-role-based-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2304.00755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.00755"}},"official":{"repos":["ringbdstack/sr-marl"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/attacking-cooperative-multi-agent","slug":"attacking-cooperative-multi-agent","title":"Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence","date":"2023-02-07","arxiv_id":"2302.03322","repositories_listed":1,"syntology":null},{"url":"/paper/transfqmix-transformers-for-leveraging-the","slug":"transfqmix-transformers-for-leveraging-the","title":"TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems","date":"2023-01-13","arxiv_id":"2301.05334","repositories_listed":1,"syntology":null},{"url":"/paper/self-motivated-multi-agent-exploration","slug":"self-motivated-multi-agent-exploration","title":"Self-Motivated Multi-Agent Exploration","date":"2023-01-05","arxiv_id":"2301.02083","repositories_listed":1,"syntology":null},{"url":"/paper/learning-credit-assignment-for-cooperative","slug":"learning-credit-assignment-for-cooperative","title":"Learning Explicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning via Polarization Policy Gradient","date":"2022-10-10","arxiv_id":"2210.05367","repositories_listed":1,"syntology":null},{"url":"/paper/a-framework-for-understanding-and-visualizing","slug":"a-framework-for-understanding-and-visualizing","title":"A Framework for Understanding and Visualizing Strategies of RL Agents","date":"2022-08-17","arxiv_id":"2208.08552","repositories_listed":1,"syntology":null},{"url":"/paper/transformer-based-value-function","slug":"transformer-based-value-function","title":"Transformer-based Value Function Decomposition for Cooperative Multi-agent Reinforcement Learning in StarCraft","date":"2022-08-15","arxiv_id":"2208.07298","repositories_listed":1,"syntology":null},{"url":"/paper/sc2egset-starcraft-ii-esport-replay-and-game","slug":"sc2egset-starcraft-ii-esport-replay-and-game","title":"SC2EGSet: StarCraft II Esport Replay and Game-state Dataset","date":"2022-07-07","arxiv_id":"2207.03428","repositories_listed":1,"syntology":null},{"url":"/paper/pac-assisted-value-factorisation-with","slug":"pac-assisted-value-factorisation-with","title":"PAC: Assisted Value Factorisation with Counterfactual Predictions in Multi-Agent Reinforcement Learning","date":"2022-06-22","arxiv_id":"2206.11420","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"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 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/pac-assisted-value-factorisation-with#ran","syntology_url":"https://syntology.ai/paper/2206.11420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.11420"}},"official":{"repos":["hanhananderson/pac-marl"],"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/on-the-limitations-of-elo-real-world-games","slug":"on-the-limitations-of-elo-real-world-games","title":"On the Limitations of Elo: Real-World Games, are Transitive, not Additive","date":"2022-06-21","arxiv_id":"2206.12301","repositories_listed":1,"syntology":null},{"url":"/paper/maser-multi-agent-reinforcement-learning-with","slug":"maser-multi-agent-reinforcement-learning-with","title":"MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer","date":"2022-06-20","arxiv_id":"2206.10607","repositories_listed":1,"syntology":null},{"url":"/paper/coach-assisted-multi-agent-reinforcement","slug":"coach-assisted-multi-agent-reinforcement","title":"Coach-assisted Multi-Agent Reinforcement Learning Framework for Unexpected Crashed Agents","date":"2022-03-16","arxiv_id":"2203.08454","repositories_listed":1,"syntology":null},{"url":"/paper/ctds-centralized-teacher-with-decentralized","slug":"ctds-centralized-teacher-with-decentralized","title":"CTDS: Centralized Teacher with Decentralized Student for Multi-Agent Reinforcement Learning","date":"2022-03-16","arxiv_id":"2203.08412","repositories_listed":1,"syntology":null},{"url":"/paper/dqmix-a-distributional-perspective-on-multi","slug":"dqmix-a-distributional-perspective-on-multi","title":"MCMARL: Parameterizing Value Function via Mixture of Categorical Distributions for Multi-Agent Reinforcement Learning","date":"2022-02-21","arxiv_id":"2202.10134","repositories_listed":1,"syntology":null},{"url":"/paper/fcmnet-full-communication-memory-net-fcmnet","slug":"fcmnet-full-communication-memory-net-fcmnet","title":"FCMNet: Full Communication Memory Net for Team-Level Cooperation in Multi-Agent Systems","date":"2022-01-28","arxiv_id":"2201.11994","repositories_listed":1,"syntology":null},{"url":"/paper/value-functions-factorization-with-latent","slug":"value-functions-factorization-with-latent","title":"Value Functions Factorization with Latent State Information Sharing in Decentralized Multi-Agent Policy Gradients","date":"2022-01-04","arxiv_id":"2201.01247","repositories_listed":1,"syntology":null},{"url":"/paper/value-function-factorisation-with-hypergraph","slug":"value-function-factorisation-with-hypergraph","title":"Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution","date":"2021-12-09","arxiv_id":"2112.06771","repositories_listed":1,"syntology":null},{"url":"/paper/offline-pre-trained-multi-agent-decision-1","slug":"offline-pre-trained-multi-agent-decision-1","title":"Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks","date":"2021-12-06","arxiv_id":"2112.02845","repositories_listed":1,"syntology":null},{"url":"/paper/regularized-softmax-deep-multi-agent-q","slug":"regularized-softmax-deep-multi-agent-q","title":"Regularized Softmax Deep Multi-Agent Q-Learning","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/coordinated-proximal-policy-optimization","slug":"coordinated-proximal-policy-optimization","title":"Coordinated Proximal Policy Optimization","date":"2021-11-07","arxiv_id":"2111.04051","repositories_listed":1,"syntology":null},{"url":"/paper/tikick-toward-playing-multi-agent-football","slug":"tikick-toward-playing-multi-agent-football","title":"TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations","date":"2021-10-09","arxiv_id":"2110.04507","repositories_listed":1,"syntology":null},{"url":"/paper/applying-supervised-and-reinforcement","slug":"applying-supervised-and-reinforcement","title":"Applying supervised and reinforcement learning methods to create neural-network-based agents for playing StarCraft II","date":"2021-09-26","arxiv_id":"2109.12691","repositories_listed":1,"syntology":null},{"url":"/paper/believe-what-you-see-implicit-constraint","slug":"believe-what-you-see-implicit-constraint","title":"Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning","date":"2021-06-07","arxiv_id":"2106.03400","repositories_listed":1,"syntology":null},{"url":"/paper/context-aware-sparse-deep-coordination-graphs","slug":"context-aware-sparse-deep-coordination-graphs","title":"Context-Aware Sparse Deep Coordination Graphs","date":"2021-06-05","arxiv_id":"2106.02886","repositories_listed":1,"syntology":null},{"url":"/paper/cooperative-multi-agent-reinforcement-5","slug":"cooperative-multi-agent-reinforcement-5","title":"Cooperative Multi-Agent Reinforcement Learning with Sequential Credit Assignment","date":"2021-05-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/an-introduction-of-mini-alphastar","slug":"an-introduction-of-mini-alphastar","title":"An Introduction of mini-AlphaStar","date":"2021-04-14","arxiv_id":"2104.06890","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/c-coma-a-continual-reinforcement-learning","slug":"c-coma-a-continual-reinforcement-learning","title":"C-COMA: A CONTINUAL REINFORCEMENT LEARNING MODEL FOR DYNAMIC MULTIAGENT ENVIRONMENTS","date":"2021-04-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tstarbot-x-an-open-sourced-and-comprehensive","slug":"tstarbot-x-an-open-sourced-and-comprehensive","title":"TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game","date":"2020-11-27","arxiv_id":"2011.13729","repositories_listed":1,"syntology":null},{"url":"/paper/tleague-a-framework-for-competitive-self-play","slug":"tleague-a-framework-for-competitive-self-play","title":"TLeague: A Framework for Competitive Self-Play based Distributed Multi-Agent Reinforcement Learning","date":"2020-11-25","arxiv_id":"2011.12895","repositories_listed":1,"syntology":null},{"url":"/paper/graph-convolutional-value-decomposition-in-1","slug":"graph-convolutional-value-decomposition-in-1","title":"Graph Convolutional Value Decomposition in Multi-Agent Reinforcement Learning","date":"2020-10-09","arxiv_id":"2010.04740","repositories_listed":1,"syntology":null},{"url":"/paper/energy-based-surprise-minimization-for-multi","slug":"energy-based-surprise-minimization-for-multi","title":"Energy-based Surprise Minimization for Multi-Agent Value Factorization","date":"2020-09-16","arxiv_id":"2009.09842","repositories_listed":1,"syntology":null},{"url":"/paper/off-policy-multi-agent-decomposed-policy","slug":"off-policy-multi-agent-decomposed-policy","title":"Off-Policy Multi-Agent Decomposed Policy Gradients","date":"2020-07-24","arxiv_id":"2007.12322","repositories_listed":1,"syntology":null},{"url":"/paper/value-decomposition-multi-agent-actor-critics","slug":"value-decomposition-multi-agent-actor-critics","title":"Value-Decomposition Multi-Agent Actor-Critics","date":"2020-07-24","arxiv_id":"2007.12306","repositories_listed":1,"syntology":null},{"url":"/paper/learning-implicit-credit-assignment-for-multi","slug":"learning-implicit-credit-assignment-for-multi","title":"Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning","date":"2020-07-06","arxiv_id":"2007.02529","repositories_listed":1,"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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/learning-implicit-credit-assignment-for-multi#ran","syntology_url":"https://syntology.ai/paper/2007.02529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.02529"}},"official":{"repos":["mzho7212/LICA"],"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/deep-implicit-coordination-graphs-for-multi","slug":"deep-implicit-coordination-graphs-for-multi","title":"Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning","date":"2020-06-19","arxiv_id":"2006.11438","repositories_listed":1,"syntology":null},{"url":"/paper/real-world-games-look-like-spinning-tops","slug":"real-world-games-look-like-spinning-tops","title":"Real World Games Look Like Spinning Tops","date":"2020-04-20","arxiv_id":"2004.09468","repositories_listed":1,"syntology":null},{"url":"/paper/meta-reinforcement-learning-with-autonomous-1","slug":"meta-reinforcement-learning-with-autonomous-1","title":"Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies","date":"2020-01-01","arxiv_id":"2001.00248","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/meta-reinforcement-learning-with-autonomous-1#ran","syntology_url":"https://syntology.ai/paper/2001.00248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.00248"}},"official":{"repos":["srsohn/msgi"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/liir-learning-individual-intrinsic-reward-in","slug":"liir-learning-individual-intrinsic-reward-in","title":"LIIR: Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/action-semantics-network-considering-the","slug":"action-semantics-network-considering-the","title":"Action Semantics Network: Considering the Effects of Actions in Multiagent Systems","date":"2019-07-26","arxiv_id":"1907.11461","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-reinforcement-learning-with-a-mind","slug":"efficient-reinforcement-learning-with-a-mind","title":"Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning","date":"2019-03-02","arxiv_id":"1903.00715","repositories_listed":1,"syntology":null},{"url":"/paper/the-natural-language-of-actions","slug":"the-natural-language-of-actions","title":"The Natural Language of Actions","date":"2019-02-04","arxiv_id":"1902.01119","repositories_listed":1,"syntology":null},{"url":"/paper/variational-saccading-efficient-inference-for","slug":"variational-saccading-efficient-inference-for","title":"Variational Saccading: Efficient Inference for Large Resolution Images","date":"2018-12-08","arxiv_id":"1812.03170","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-common-knowledge-reinforcement","slug":"multi-agent-common-knowledge-reinforcement","title":"Multi-Agent Common Knowledge Reinforcement Learning","date":"2018-10-27","arxiv_id":"1810.11702","repositories_listed":1,"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/multi-agent-common-knowledge-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1810.11702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.11702"}},"official":{"repos":["schroederdewitt/mackrl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-rts-a-game-environment-for-deep","slug":"deep-rts-a-game-environment-for-deep","title":"Deep RTS: A Game Environment for Deep Reinforcement Learning in Real-Time Strategy Games","date":"2018-08-15","arxiv_id":"1808.05032","repositories_listed":1,"syntology":null},{"url":null,"slug":"language-guided-multi-agent-learning-in","title":"Language-Guided Multi-Agent Learning in Simulations: A Unified Framework and Evaluation","date":"2025-06-01","arxiv_id":"2506.04251","repositories_listed":0,"syntology":null},{"url":null,"slug":"reflection-of-episodes-learning-to-play-game","title":"Reflection of Episodes: Learning to Play Game from Expert and Self Experiences","date":"2025-02-19","arxiv_id":"2502.13388","repositories_listed":0,"syntology":null},{"url":null,"slug":"superhuman-ai-disclosure-impacts-on-toxicity","title":"Superhuman Game AI Disclosure: Expertise and Context Moderate Effects on Trust and Fairness","date":"2025-01-31","arxiv_id":"2503.15514","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-like-bots-for-tactical-shooters-using","title":"Human-like Bots for Tactical Shooters Using Compute-Efficient Sensors","date":"2024-12-30","arxiv_id":"2501.00078","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficiently-scanning-and-resampling-spatio","title":"Efficiently Scanning and Resampling Spatio-Temporal Tasks with Irregular Observations","date":"2024-10-11","arxiv_id":"2410.08681","repositories_listed":0,"syntology":null},{"url":null,"slug":"comadice-offline-cooperative-multi-agent","title":"ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization","date":"2024-10-02","arxiv_id":"2410.01954","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-stateful-value-factorization-in-multi","title":"On Stateful Value Factorization in Multi-Agent Reinforcement Learning","date":"2024-08-27","arxiv_id":"2408.15381","repositories_listed":0,"syntology":null},{"url":null,"slug":"powqmix-weighted-value-factorization-with","title":"POWQMIX: Weighted Value Factorization with Potentially Optimal Joint Actions Recognition for Cooperative Multi-Agent Reinforcement Learning","date":"2024-05-13","arxiv_id":"2405.08036","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-ai-teaming-in-unknown","title":"Collaborative AI Teaming in Unknown Environments via Active Goal Deduction","date":"2024-03-22","arxiv_id":"2403.15341","repositories_listed":0,"syntology":null},{"url":null,"slug":"smaug-a-sliding-multidimensional-task-window","title":"SMAUG: A Sliding Multidimensional Task Window-Based MARL Framework for Adaptive Real-Time Subtask Recognition","date":"2024-03-04","arxiv_id":"2403.01816","repositories_listed":0,"syntology":null}],"syntology_records":24,"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":22,"papers_where_code_ran_first_page":"/task/starcraft-ii/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":2,"url":"/task/starcraft-ii/papers/2","json":"/task/starcraft-ii/papers/2.json","rows":75},{"order":"ran","page":1,"of":1,"url":"/task/starcraft-ii/papers/ran/1","json":"/task/starcraft-ii/papers/ran/1.json","rows":22}],"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":"1521191a8b91446a26ea2e6a5803ab5a3f8665128e6d235fe4fc6e77bc25dfe4","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}