ResearchBenchmarksOffline Reinforcement Learning on D4RL AntMaze umaze-diverse v2 (test)Follow84Score (Normalized)CQL-3.3619.324264.68Mar 12, 2024Evaluation ResultsMethodMethodLinksScore (Normalized)CQL2024.0384A2PO2024.0372.6TD3+BC2024.0371.4Diffusion-QL2024.0366.2IQL2024.0362.2BCQ2024.0355CQL+AW2024.0354EQL2024.0350.8AWAC2024.0349.3BC2024.0345.6MOPO2024.030LAPO2024.030