{"url":"/task/starcraft","name":"Starcraft","slug":"starcraft","description_markdown":"Starcraft I 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: [Macro Action Selection with Deep Reinforcement Learning in StarCraft](https://arxiv.org/pdf/1812.00336v3.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":311,"papers_with_code":148,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":8,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/vizdoom","name":"VizDoom","full_name":"VizDoom","num_papers_in_archive":156},{"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/mario-ai","name":"Mario AI","full_name":"Mario AI","num_papers_in_archive":11},{"url":"/dataset/msc","name":"MSC","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/stardata","name":"StarData","full_name":"StarData","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"}],"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":148,"tagged_in_all":311,"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/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/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/counterfactual-multi-agent-policy-gradients","title":"Counterfactual Multi-Agent Policy Gradients","date":"2017-05-24","arxiv_id":"1705.08926","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"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/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/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/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/learning-when-to-communicate-at-scale-in","title":"Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks","date":"2018-12-23","arxiv_id":"1812.09755","repositories_listed":3,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/towards-accurate-generative-models-of-video-a","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","date":"2018-12-03","arxiv_id":"1812.01717","repositories_listed":3,"syntology":null},{"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/value-based-ctde-methods-in-symmetric-two","title":"Value-based CTDE Methods in Symmetric Two-team Markov Game: from Cooperation to Team Competition","date":"2022-11-21","arxiv_id":"2211.11886","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/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/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/learning-to-play-no-press-diplomacy-with-best","title":"Learning to Play No-Press Diplomacy with Best Response Policy Iteration","date":"2020-06-08","arxiv_id":"2006.04635","repositories_listed":2,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/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_unverified":4,"n_pointer_only":0}},{"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}],"syntology_records":15,"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"}}