Multi-agent Offline Reinforcement Learning on MPE PP (Random) benchmark leaderboard · SOTA2 Research

Multi-agent Offline Reinforcement Learning on MPE PP (Random)

92.8ScorePLCQL

Evaluation Results

Method	Links
PLCQL2026.03		92.8
SPaCQL2026.03		89.4
CFCQL2023.09		78.5
CFCQL2026.03		78.5
MACQL2023.09		25.2
MACQL2026.03		25.2
DoF2026.03		16.5
OMAR2023.09		11.1
OMAR2026.03		11.1
MATD3-BC2023.09		5.7
MA-TD3+BC2026.03		5.7
ICQL2023.09		5
MAICQ2023.09		2.2
IQL2023.09		1.3
IQL2026.03		1.3
AWAC2023.09		0.2