{"url":"/dataset/smac-def-infantry-sequential","name":"Def_Infantry_sequential","full_name":null,"description_markdown":"SMAC+ defensive infantry scenario with sequential episodic buffer","description_withheld":null,"homepage":"","introduced_date":"2022-07-05","introduced_date_note":null,"introduced_by":{"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","first_author":"Mingyu Kim","url":null},"license":null,"modalities":[],"tasks":[{"name":"SMAC+","url":"/task/smac-1","datasets_with_task":"/datasets/task/smac-1"}],"languages":[],"variants":["Def_Infantry_sequential"],"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-sequential","task":"SMAC+","dataset_variant":"Def_Infantry_sequential","rows":11,"metrics":["Median Win Rate"],"first_row_in_archive_order":{"model":"MADDPG","paper":"/paper/multi-agent-actor-critic-for-mixed","metrics":{"Median Win Rate":"100"},"code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"openai/multiagent-particle-envs","url":"https://github.com/openai/multiagent-particle-envs"},{"title":"openai/maddpg","url":"https://github.com/openai/maddpg"},{"title":"xuehy/pytorch-maddpg","url":"https://github.com/xuehy/pytorch-maddpg"},{"title":"shariqiqbal2810/maddpg-pytorch","url":"https://github.com/shariqiqbal2810/maddpg-pytorch"},{"title":"starry-sky6688/MADDPG","url":"https://github.com/starry-sky6688/MADDPG"},{"title":"facebookresearch/benchmarl","url":"https://github.com/facebookresearch/benchmarl"},{"title":"philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients","url":"https://github.com/philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients"},{"title":"cyanrain7/trpo-in-marl","url":"https://github.com/cyanrain7/trpo-in-marl"},{"title":"cyanrain7/trust-region-policy-optimisation-in-multi-agent-reinforcement-learning","url":"https://github.com/cyanrain7/trust-region-policy-optimisation-in-multi-agent-reinforcement-learning"},{"title":"JohannesAck/tf2multiagentrl","url":"https://github.com/JohannesAck/tf2multiagentrl"},{"title":"isp1tze/MAProj","url":"https://github.com/isp1tze/MAProj"},{"title":"JohannesAck/MATD3implementation","url":"https://github.com/JohannesAck/MATD3implementation"},{"title":"thechrisyoon08/Multi-agent-reinforcement-learning","url":"https://github.com/thechrisyoon08/Multi-agent-reinforcement-learning"},{"title":"thechrisyoon08/marl","url":"https://github.com/thechrisyoon08/marl"},{"title":"cyoon1729/Multi-agent-reinforcement-learning","url":"https://github.com/cyoon1729/Multi-agent-reinforcement-learning"},{"title":"quantumiracle/mars","url":"https://github.com/quantumiracle/mars"},{"title":"shariqiqbal2810/multiagent-particle-envs","url":"https://github.com/shariqiqbal2810/multiagent-particle-envs"},{"title":"morning9393/HAPPO-HATRPO","url":"https://github.com/morning9393/HAPPO-HATRPO"},{"title":"google/maddpg-replication","url":"https://github.com/google/maddpg-replication"},{"title":"caslab-vt/SARNet","url":"https://github.com/caslab-vt/SARNet"},{"title":"qi-pang/mdpfuzz","url":"https://github.com/qi-pang/mdpfuzz"},{"title":"pr-shukla/maddpg-keras","url":"https://github.com/pr-shukla/maddpg-keras"},{"title":"gingkg/multiagent-particle-envs","url":"https://github.com/gingkg/multiagent-particle-envs"},{"title":"jyqhahah/rl_maddpg_matd3","url":"https://github.com/jyqhahah/rl_maddpg_matd3"},{"title":"baoqianwang/iros22_darl1n","url":"https://github.com/baoqianwang/iros22_darl1n"},{"title":"zowiezhang/stas","url":"https://github.com/zowiezhang/stas"},{"title":"yannbouteiller/gym-airsimdroneracinglab","url":"https://github.com/yannbouteiller/gym-airsimdroneracinglab"},{"title":"anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","url":"https://github.com/anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning"},{"title":"schroederdewitt/multiagent-particle-envs","url":"https://github.com/schroederdewitt/multiagent-particle-envs"},{"title":"EyaRhouma/collaboration-competition-MADDPG","url":"https://github.com/EyaRhouma/collaboration-competition-MADDPG"},{"title":"zoeyuchao/MPE-pytorch","url":"https://github.com/zoeyuchao/MPE-pytorch"},{"title":"bonniesjli/MADDPG_Tennis","url":"https://github.com/bonniesjli/MADDPG_Tennis"},{"title":"bonniesjli/MADDPG_Tennis_UnityML","url":"https://github.com/bonniesjli/MADDPG_Tennis_UnityML"},{"title":"semitable/multiagent-particle-envs","url":"https://github.com/semitable/multiagent-particle-envs"},{"title":"kargarisaac/macrpo","url":"https://github.com/kargarisaac/macrpo"},{"title":"madras-simulator/Multi-Agent-Particle-Environment","url":"https://github.com/madras-simulator/Multi-Agent-Particle-Environment"},{"title":"wsjeon/multiagent-particle-envs-maac","url":"https://github.com/wsjeon/multiagent-particle-envs-maac"},{"title":"NeuroCSUT/intentions","url":"https://github.com/NeuroCSUT/intentions"},{"title":"marwanihab/RL_Tag_Game","url":"https://github.com/marwanihab/RL_Tag_Game"},{"title":"zoeyuchao/MPEnew-pytorch","url":"https://github.com/zoeyuchao/MPEnew-pytorch"},{"title":"lachisis/multiagent-particle-envs","url":"https://github.com/lachisis/multiagent-particle-envs"},{"title":"Stippler/cow-simulator","url":"https://github.com/Stippler/cow-simulator"},{"title":"biorobotics/PRD_environments","url":"https://github.com/biorobotics/PRD_environments"},{"title":"raoshashank/Tennis-with-MADDPG","url":"https://github.com/raoshashank/Tennis-with-MADDPG"},{"title":"Steven-Ho/multiagent-particle-envs","url":"https://github.com/Steven-Ho/multiagent-particle-envs"},{"title":"sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3","url":"https://github.com/sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3"},{"title":"Ah31/maddpg_pytorch","url":"https://github.com/Ah31/maddpg_pytorch"},{"title":"karishnu/tf-agents-multi-particle-envs","url":"https://github.com/karishnu/tf-agents-multi-particle-envs"},{"title":"SihongHo/multiagent-particle-envs","url":"https://github.com/SihongHo/multiagent-particle-envs"},{"title":"wsjeon/multiagent-particle-envs-v2","url":"https://github.com/wsjeon/multiagent-particle-envs-v2"},{"title":"baicenxiao/shaping-advice","url":"https://github.com/baicenxiao/shaping-advice"},{"title":"Yutongamber/MADDPG","url":"https://github.com/Yutongamber/MADDPG"},{"title":"SintolRTOS/multi-agent_Example","url":"https://github.com/SintolRTOS/multi-agent_Example"},{"title":"Chan1998/MAAC","url":"https://github.com/Chan1998/MAAC"},{"title":"Abdelhamid-bouzid/Multi-Agent-Deep-Deterministic-Policy-Gradient","url":"https://github.com/Abdelhamid-bouzid/Multi-Agent-Deep-Deterministic-Policy-Gradient"},{"title":"debajit15kgp/multiagent-envs","url":"https://github.com/debajit15kgp/multiagent-envs"},{"title":"johannesharmse/multi_agent_RL","url":"https://github.com/johannesharmse/multi_agent_RL"},{"title":"jingdic/rgmcomm","url":"https://github.com/jingdic/rgmcomm"},{"title":"rainandwind1/Maddpg_multiagent","url":"https://github.com/rainandwind1/Maddpg_multiagent"},{"title":"kishorkuttan/Multi-Agent-Deep-Deterministic-Policy-Gradient-actor-critic-deep-reinforcement-for-capacity-manageme","url":"https://github.com/kishorkuttan/Multi-Agent-Deep-Deterministic-Policy-Gradient-actor-critic-deep-reinforcement-for-capacity-manageme"},{"title":"dtabas/multiagent-particle-envs","url":"https://github.com/dtabas/multiagent-particle-envs"},{"title":"goldbattle/snakes_mal","url":"https://github.com/goldbattle/snakes_mal"},{"title":"ksajan/DDPG-MAPE","url":"https://github.com/ksajan/DDPG-MAPE"},{"title":"rainandwind1/MERL","url":"https://github.com/rainandwind1/MERL"},{"title":"darshil333/CSE574","url":"https://github.com/darshil333/CSE574"},{"title":"rallen10/multiagent-particle-envs","url":"https://github.com/rallen10/multiagent-particle-envs"},{"title":"tkarr21/multagent-particle-envs","url":"https://github.com/tkarr21/multagent-particle-envs"},{"title":"mauricemager/multiagent-robot","url":"https://github.com/mauricemager/multiagent-robot"},{"title":"tkarr21/multiagent-particle-envs","url":"https://github.com/tkarr21/multiagent-particle-envs"},{"title":"petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity","url":"https://github.com/petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity"},{"title":"MrDaubinet/collaboration-and-competition","url":"https://github.com/MrDaubinet/collaboration-and-competition"},{"title":"LXYYY/multiagent-particle-envs","url":"https://github.com/LXYYY/multiagent-particle-envs"},{"title":"Zorrorulz/MultiAgentDDPG-Tennis","url":"https://github.com/Zorrorulz/MultiAgentDDPG-Tennis"},{"title":"biemann/Collaboration-and-Competition","url":"https://github.com/biemann/Collaboration-and-Competition"},{"title":"hepengli/multiagent-particle-envs","url":"https://github.com/hepengli/multiagent-particle-envs"},{"title":"jiayu-ch15/MPE-for-curriculum-learning","url":"https://github.com/jiayu-ch15/MPE-for-curriculum-learning"},{"title":"marwanihab/RL_Testing_Noise_ASRN","url":"https://github.com/marwanihab/RL_Testing_Noise_ASRN"},{"title":"AleXander-Tsui/MPE","url":"https://github.com/AleXander-Tsui/MPE"},{"title":"madhur-tandon/RL-Project","url":"https://github.com/madhur-tandon/RL-Project"},{"title":"rainandwind1/MADDPG-reconstruct","url":"https://github.com/rainandwind1/MADDPG-reconstruct"},{"title":"RL-WFU/multi_agent_attack","url":"https://github.com/RL-WFU/multi_agent_attack"},{"title":"JinTanda/MADDPG_env","url":"https://github.com/JinTanda/MADDPG_env"},{"title":"jansenkeith501/CS295-MADDPG","url":"https://github.com/jansenkeith501/CS295-MADDPG"},{"title":"baradist/multiagent-particle-envs","url":"https://github.com/baradist/multiagent-particle-envs"},{"title":"krasing/DRLearningCollaboration","url":"https://github.com/krasing/DRLearningCollaboration"}]},"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":3,"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/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/multi-agent-actor-critic-for-mixed","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","date":"2017-06-07","rows_on_this_dataset":1,"code_links":86,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":143,"samples_ran":75,"samples_unverified":68,"pointer_only_for_licence":99,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"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":157,"samples_ran":86,"samples_unverified":71,"pointer_only_for_licence":107,"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."}