{"url":"/dataset/smac","name":"SMAC","full_name":"The StarCraft Multi-Agent Challenge","description_markdown":"The StarCraft Multi-Agent Challenge (SMAC) is a benchmark that provides elements of partial observability, challenging dynamics, and high-dimensional observation spaces. SMAC is built using the StarCraft II game engine, creating a testbed for research in cooperative MARL where each game unit is an independent RL agent.","description_withheld":null,"homepage":"https://paperswithcode.com/task/smac","introduced_date":"2019-02-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-starcraft-multi-agent-challenge","title":"The StarCraft Multi-Agent Challenge","first_author":"Mikayel Samvelyan","url":null},"license":null,"modalities":[],"tasks":[{"name":"SMAC","url":"/task/smac","datasets_with_task":"/datasets/task/smac"}],"languages":[],"variants":["SMAC MMM2","SMAC 6h_vs_8z","SMAC 3s5z_vs_3s6z","SMAC corridor","SMAC 27m_vs_30m","SMAC"],"data_loaders":[],"num_papers_in_archive":324,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/smac-on-smac-6h-vs-8z-1","task":"SMAC","dataset_variant":"SMAC 6h_vs_8z","rows":14,"metrics":["Median Win Rate","Average Score"],"first_row_in_archive_order":{"model":"ACE","paper":"/paper/ace-cooperative-multi-agent-q-learning-with","metrics":{"Median Win Rate":"93.75"},"code_links":[{"title":"opendilab/ace","url":"https://github.com/opendilab/ace"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/smac-on-smac-mmm2-1","task":"SMAC","dataset_variant":"SMAC MMM2","rows":14,"metrics":["Median Win Rate","Average Score"],"first_row_in_archive_order":{"model":"ACE","paper":"/paper/ace-cooperative-multi-agent-q-learning-with","metrics":{"Median Win Rate":"100"},"code_links":[{"title":"opendilab/ace","url":"https://github.com/opendilab/ace"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/smac-on-smac-3s5z-vs-3s6z-1","task":"SMAC","dataset_variant":"SMAC 3s5z_vs_3s6z","rows":13,"metrics":["Median Win Rate","Average Score"],"first_row_in_archive_order":{"model":"ACE","paper":"/paper/ace-cooperative-multi-agent-q-learning-with","metrics":{"Median Win Rate":"100"},"code_links":[{"title":"opendilab/ace","url":"https://github.com/opendilab/ace"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/smac-on-smac-corridor","task":"SMAC","dataset_variant":"SMAC corridor","rows":13,"metrics":["Median Win Rate","Average Score"],"first_row_in_archive_order":{"model":"ACE","paper":"/paper/ace-cooperative-multi-agent-q-learning-with","metrics":{"Median Win Rate":"100"},"code_links":[{"title":"opendilab/ace","url":"https://github.com/opendilab/ace"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/smac-on-smac-27m-vs-30m","task":"SMAC","dataset_variant":"SMAC 27m_vs_30m","rows":11,"metrics":["Median Win Rate","Average Score"],"first_row_in_archive_order":{"model":"DDN","paper":"/paper/dfac-framework-factorizing-the-value-function","metrics":{"Average Score":"19.71","Median Win Rate":"91.48"},"code_links":[{"title":"j3soon/dfac","url":"https://github.com/j3soon/dfac"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/a-unified-framework-for-factorizing","title":"A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning","date":"2023-06-04","rows_on_this_dataset":10,"code_links":1,"syntology":null},{"paper":"/paper/ace-cooperative-multi-agent-q-learning-with","title":"ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency","date":"2022-11-29","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dfac-framework-factorizing-the-value-function","title":"DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning","date":"2021-02-16","rows_on_this_dataset":30,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/monotonic-value-function-factorisation-for","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","date":"2020-03-19","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/the-starcraft-multi-agent-challenge","title":"The StarCraft Multi-Agent Challenge","date":"2019-02-11","rows_on_this_dataset":16,"code_links":23,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":6,"samples_unverified":9,"pointer_only_for_licence":13,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":4,"samples_harvested":21,"samples_ran":8,"samples_unverified":13,"pointer_only_for_licence":13,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}