{"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_unverified":0,"n_pointer_only":2}}},{"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_unverified":0,"n_pointer_only":2}}},{"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_unverified":2,"n_pointer_only":6}}}],"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":90,"tagged_in_all":175,"items":[{"url":"/paper/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":6,"n_unverified":9,"n_pointer_only":13}},{"url":"/paper/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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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_unverified":2,"n_pointer_only":6}},{"url":"/paper/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_unverified":0,"n_pointer_only":2}},{"url":"/paper/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_unverified":4,"n_pointer_only":0}},{"url":"/paper/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":4,"n_unverified":4,"n_pointer_only":4}},{"url":"/paper/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":2,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/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","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":0,"n_unverified":23,"n_pointer_only":0}},{"url":"/paper/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":1,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/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","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":0,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/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","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","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","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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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","title":"Deep Coordination Graphs","date":"2019-09-27","arxiv_id":"1910.00091","repositories_listed":2,"syntology":null},{"url":"/paper/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","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","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","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","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","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","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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","title":"Carefully Structured Compression: Efficiently Managing StarCraft II Data","date":"2024-10-11","arxiv_id":"2410.08659","repositories_listed":1,"syntology":null}],"syntology_records":12,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}