paper-with-me

SMAC+ 벤치마크

SMAC+ on Def_Outnumbered_sequential

22개 결과 · ⬇ CSV · JSON

Median Win Rate

0 25 50 75 100 2017-05 2026-09 COMA — 0.0 (2017-05-24) COMA — 0.0 (2017-05-24) MADDPG — 81.3 (2017-06-07) MADDPG — 81.3 (2017-06-07) VDN — 15.6 (2017-06-16) VDN — 15.6 (2017-06-16) QMIX — 0.0 (2018-03-30) QMIX — 0.0 (2018-03-30) QTRAN — 81.3 (2019-05-14) QTRAN — 81.3 (2019-05-14) DDN — 0.0 (2021-02-16) DIQL — 0.0 (2021-02-16) DMIX — 0.0 (2021-02-16) DDN — 0.0 (2021-02-16) DIQL — 0.0 (2021-02-16) DMIX — 0.0 (2021-02-16) MASAC — 0.0 (2021-04-14) MASAC — 0.0 (2021-04-14) DRIMA — 100.0 (2021-09-29) DRIMA — 100.0 (2021-09-29) IQL — 0.0 (2022-07-05) IQL — 0.0 (2022-07-05) COMA — 0.0 (2017-05-24) MADDPG — 81.3 (2017-06-07) DRIMA — 100.0 (2021-09-29)
RankModel Median Win Rate PaperCodeYear
1 DRIMA 100 Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning 2021
2 MADDPG 81.3 Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments ray-project/ray · openai/multiagent-particle-envs · openai/maddpg · +83 2017
2 QTRAN 81.3 QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning opendilab/DI-engine · hhhusiyi-monash/UPDeT · Sonkyunghwan/QTRAN · +1 2019
4 VDN 15.6 Value-Decomposition Networks For Cooperative Multi-Agent Learning facebookresearch/benchmarl · tjuhaoxiaotian/pymarl3 · hhhusiyi-monash/UPDeT · +7 2017
5 COMA 0.0 Counterfactual Multi-Agent Policy Gradients opendilab/DI-engine · TonghanWang/NDQ · matteokarldonati/Counterfactual-Multi-Agent-Policy-Gradients · +4 2017
5 QMIX 0.0 QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning ray-project/ray · opendilab/DI-engine · oxwhirl/pymarl · +15 2018
5 MASAC 0.0 Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning puyuan1996/MARL 2021
5 IQL 0.0 The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions osilab-kaist/smac_exp 2022
5 DDN 0.0 DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning j3soon/dfac 2021
5 DIQL 0.0 DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning j3soon/dfac 2021
5 DMIX 0.0 DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning j3soon/dfac 2021
12 DRIMA 100 Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning 2021
13 MADDPG 81.3 Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments ray-project/ray · openai/multiagent-particle-envs · openai/maddpg · +83 2017
13 QTRAN 81.3 QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning opendilab/DI-engine · hhhusiyi-monash/UPDeT · Sonkyunghwan/QTRAN · +1 2019
15 VDN 15.6 Value-Decomposition Networks For Cooperative Multi-Agent Learning facebookresearch/benchmarl · tjuhaoxiaotian/pymarl3 · hhhusiyi-monash/UPDeT · +7 2017
16 COMA 0.0 Counterfactual Multi-Agent Policy Gradients opendilab/DI-engine · TonghanWang/NDQ · matteokarldonati/Counterfactual-Multi-Agent-Policy-Gradients · +4 2017
16 QMIX 0.0 QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning ray-project/ray · opendilab/DI-engine · oxwhirl/pymarl · +15 2018
16 MASAC 0.0 Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning puyuan1996/MARL 2021
16 IQL 0.0 The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions osilab-kaist/smac_exp 2022
16 DDN 0.0 DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning j3soon/dfac 2021
1–20 / 22 다음 → 페이지당 10 20 50 100