List your company
ResearchFormerly WizWand

Multi-agent Offline Reinforcement Learning on MPE PP (Medium-replay)

87.3ScorePLCQL
5.1426.4747.869.13Sep 22, 2023Feb 22, 2024Jul 24, 2024Dec 25, 2024May 27, 2025Oct 27, 2025Mar 30, 2026
Updated 7mo ago

Evaluation results

MethodLinks
PLCQL2026.0387.3
SPaCQL2026.0375
CFCQL2023.0971.1
CFCQL2026.0371.1
DoF2026.0365.4
OMAR2023.0947.1
OMAR2026.0347.1
MAICQ2023.0934.5
MATD3-BC2023.0928.7
MA-TD3+BC2026.0328.7
ICQL2023.0924.8
IQL2023.0923.2
IQL2026.0323.2
MACQL2023.0911.9
MACQL2026.0311.9
AWAC2023.098.3