paper-with-me

SMAC+ 벤치마크

SMAC+ on Off_Near_sequential

8개 결과 · ⬇ CSV · JSON

Median Win Rate

0 23.45 46.9 70.35 93.8 2017-05 2026-09 COMA — 0.0 (2017-05-24) COMA — 0.0 (2017-05-24) MADDPG — 75.0 (2017-06-07) MADDPG — 75.0 (2017-06-07) QMIX — 90.6 (2018-03-30) QMIX — 90.6 (2018-03-30) DRIMA — 93.8 (2021-09-29) DRIMA — 93.8 (2021-09-29) COMA — 0.0 (2017-05-24) MADDPG — 75.0 (2017-06-07) QMIX — 90.6 (2018-03-30) DRIMA — 93.8 (2021-09-29)
RankModel Median Win Rate PaperCodeYear
1 DRIMA 93.8 Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning 2021
2 QMIX 90.6 QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning ray-project/ray · opendilab/DI-engine · oxwhirl/pymarl · +15 2018
3 MADDPG 75.0 Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments ray-project/ray · openai/multiagent-particle-envs · openai/maddpg · +83 2017
4 COMA 0.0 Counterfactual Multi-Agent Policy Gradients opendilab/DI-engine · TonghanWang/NDQ · matteokarldonati/Counterfactual-Multi-Agent-Policy-Gradients · +4 2017
5 DRIMA 93.8 Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning 2021
6 QMIX 90.6 QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning ray-project/ray · opendilab/DI-engine · oxwhirl/pymarl · +15 2018
7 MADDPG 75.0 Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments ray-project/ray · openai/multiagent-particle-envs · openai/maddpg · +83 2017
8 COMA 0.0 Counterfactual Multi-Agent Policy Gradients opendilab/DI-engine · TonghanWang/NDQ · matteokarldonati/Counterfactual-Multi-Agent-Policy-Gradients · +4 2017
1–8 / 8 페이지당 10 20 50 100