Multi-agent Offline Reinforcement Learning on MPE Cooperative Navigation (CN) v1 (Med-Rep) benchmark leaderboard · SOTA2 Research

Multi-agent Offline Reinforcement Learning on MPE Cooperative Navigation (CN) v1 (Med-Rep)

95.4ScorePLCQL

Evaluation Results

Method	Links
PLCQL2026.03		95.4
SPaCQL2026.03		71.9
DoF2026.03		57.4
CFCQL2023.09		52.2
CFCQL2026.03		52.2
OMAR2023.09		37.9
OMAR2026.03		37.9
MACQL2023.09		25.5
MACQL2026.03		25.5
ICQL2023.09		20
MATD3-BC2023.09		15.4
MA-TD3+BC2026.03		15.4
MAICQ2023.09		13.6
IQL2023.09		10.8
IQL2026.03		10.8
AWAC2023.09		2.7