ResearchBenchmarksOffline Reinforcement Learning on MuJoCo Hopper Medium-Replay v2Follow100.02Avg Normalized ScorePPLR14.823236.941659.0681.1784Oct 17, 2024Evaluation ResultsMethodMethodLinksAvg Normalized ScorePPLR2024.10100.02ReBRAC2024.1098.1One-RL2024.1097.5CQL2024.1095IQL2024.1094.7OTR+IQL2024.1084.8TD3+BC2024.1060.9BC2024.1018.1