ResearchBenchmarksLocomotion on D4RL Hopper-expertFollow113.08Score (Normalized)O2PPO91.29296.9485102.605108.2615Dec 25, 2024Evaluation ResultsMethodMethodLinksScore (Normalized)Score Change (Delta)O2PPOOnline update way=IQLOnline update way=IQL2024.12113.089.09O2SACOnline update way=SACOnline update way=SAC2024.12112.760.95Off2OnOnline update way=SACOnline update way=SAC2024.1292.13-19.44