ResearchBenchmarksLocomotion on D4RL halfcheetah-random-expertFollow90.3Normalized ScoreA2PO-2.2621.7745.869.83Mar 12, 2024Evaluation ResultsMethodMethodLinksNormalized ScoreA2PO2024.0390.3IQL+ReD2024.0342.4DT2024.0310.3%BC2024.037.7PRDC2024.031.3