Multi-agent Offline Reinforcement Learning on MPE World Expert benchmark leaderboard · SOTA2 Research

Multi-agent Offline Reinforcement Learning on MPE World Expert

135.2ScoreDoF

Evaluation Results

Method	Links
DoF2026.03		135.2
PLCQL2026.03		133
CFCQL2023.09		119.7
CFCQL2026.03		119.7
SPaCQL2026.03		112.3
OMAR2023.09		110.4
OMAR2026.03		110.4
MATD3-BC2023.09		110.3
MA-TD3+BC2026.03		110.3
MAICQ2023.09		109.5
IQL2023.09		107.8
IQL2026.03		107.8
AWAC2023.09		107.6
MACQL2023.09		99.7
MACQL2026.03		99.7
ICQL2023.09		71.9