Multi-agent Offline Reinforcement Learning on MPE PP Medium benchmark leaderboard · SOTA2 Research

Multi-agent Offline Reinforcement Learning on MPE PP Medium

86.3ScoreDoF

Evaluation Results

Method	Links
DoF2026.03		86.3
PLCQL2026.03		84
CFCQL2023.09		68.5
CFCQL2026.03		68.5
OMAR2023.09		66.7
OMAR2026.03		66.7
MATD3-BC2023.09		65.1
MA-TD3+BC2026.03		65.1
MAICQ2023.09		63.3
SPaCQL2026.03		61.9
ICQL2023.09		61.7
MACQL2023.09		55
MACQL2026.03		55
IQL2023.09		53.6
IQL2026.03		53.6
AWAC2023.09		50.9