ResearchBenchmarksOffline Reinforcement Learning on D4RL Adroit Total v1 (test)Follow153.9Normalized ScoreA2PO-11.87631.16274.2117.238Mar 12, 2024Evaluation ResultsMethodMethodLinksNormalized ScoreA2PO2024.03153.9Diffusion-QL2024.03130.1LAPO2024.03123.9IQL2024.03108.8BC2024.0391.3EQL2024.0391.2CQL2024.0376.7MOPO2024.0365.3BCQ2024.0340.3AWAC2024.033.5TD3+BC2024.03-2CQL+AW2024.03-5.5