{"url":"/dataset/smac-def-infantry-parallel","name":"Def_Infantry_parallel","full_name":"SMAC+_Def_Infantry_parallel_20","description_markdown":"smac+ defense infantry scenario with parallel episodic buffer","description_withheld":null,"homepage":"","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"Apache 2.0","url":null},"modalities":[],"tasks":[{"name":"SMAC+","url":"/task/smac-1","datasets_with_task":"/datasets/task/smac-1"}],"languages":[],"variants":["Def_Infantry_parallel"],"data_loaders":[],"num_papers_in_archive":9,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/smac-on-smac-def-infantry-parallel","task":"SMAC+","dataset_variant":"Def_Infantry_parallel","rows":10,"metrics":["Median Win Rate"],"first_row_in_archive_order":{"model":"QTRAN","paper":"/paper/qtran-learning-to-factorize-with","metrics":{"Median Win Rate":"100.0"},"code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/qtran.py"},{"title":"hhhusiyi-monash/UPDeT","url":"https://github.com/hhhusiyi-monash/UPDeT"},{"title":"Sonkyunghwan/QTRAN","url":"https://github.com/Sonkyunghwan/QTRAN"},{"title":"jugg1er/air","url":"https://github.com/jugg1er/air"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/the-starcraft-multi-agent-challenges-learning","title":"The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions","date":"2022-07-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/disentangling-sources-of-risk-for","title":"Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning","date":"2021-09-29","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/decomposed-soft-actor-critic-method-for","title":"Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning","date":"2021-04-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":2,"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/qtran-learning-to-factorize-with","title":"QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning","date":"2019-05-14","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dfanet-deep-feature-aggregation-for-real-time","title":"DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation","date":"2019-04-03","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/qmix-monotonic-value-function-factorisation","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","date":"2018-03-30","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":9,"samples_unverified":2,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/value-decomposition-networks-for-cooperative","title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","date":"2017-06-16","rows_on_this_dataset":1,"code_links":10,"syntology":null},{"paper":"/paper/counterfactual-multi-agent-policy-gradients","title":"Counterfactual Multi-Agent Policy Gradients","date":"2017-05-24","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"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":5,"samples_harvested":15,"samples_ran":12,"samples_unverified":3,"pointer_only_for_licence":9,"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."}