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

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

85.1ScorePLCQL

Evaluation Results

Method	Links
PLCQL2026.03		85.1
SPaCQL2026.03		78.6
DoF2026.03		75.6
CFCQL2023.09		65
CFCQL2026.03		65
OMAR2023.09		47.9
OMAR2026.03		47.9
ICQL2023.09		34.1
MAICQ2023.09		29.3
MATD3-BC2023.09		29.3
MA-TD3+BC2026.03		29.3
IQL2023.09		28.2
IQL2026.03		28.2
AWAC2023.09		25.7
MACQL2023.09		14.3
MACQL2026.03		14.3