ResearchBenchmarksLocomotion on D4RL Walker2d-expertFollow120.35Normalized Score (100k Steps)O2SAC117.3756118.1478118.92119.6922Dec 25, 2024Evaluation ResultsMethodMethodLinksNormalized Score (100k Steps)Score Increase (Delta)O2SACOnline update way=SACOnline update way=SAC2024.12120.3510.5Off2OnOnline update way=SACOnline update way=SAC2024.12118.028.3O2PPOOnline update way=IQLOnline update way=IQL2024.12117.499.27