Multi-agent Offline Reinforcement Learning on MPE CN (Expert) benchmark leaderboard · SOTA2 Research

Multi-agent Offline Reinforcement Learning on MPE CN (Expert)

136.4ScoreDoF

Evaluation Results

Method	Links
DoF2026.03		136.4
OMAR2023.09		114.9
OMAR2026.03		114.9
CFCQL2023.09		112
CFCQL2026.03		112
SPaCQL2026.03		111.9
PLCQL2026.03		110.9
MATD3-BC2023.09		108.3
MA-TD3+BC2026.03		108.3
MAICQ2023.09		104
IQL2023.09		103.7
IQL2026.03		103.7
AWAC2023.09		103.3
ICQL2023.09		98.2
MACQL2023.09		12.2
MACQL2026.03		12.2