ResearchBenchmarksOffline Reinforcement Learning on D4RL Antmaze large-play v2Offline Reinforcement Learning on D4RL Antmaze large-play v2Follow62Averaged ScoreDTAMP23.20833.27943.3553.421Dec 6, 2023Evaluation resultsMethodMethodLinksAveraged ScorePerformance Difference vs Single-Goal (%)DTAMPGoal Setting=multi-goalGoal Setting=multi-goal2023.1262-22.5IQL+HERGoal Setting=multi-goa...Goal Setting=multi-goal, Hindsight Experience Replay=true2023.124616.2TT+IQLGoal Setting=multi-goalGoal Setting=multi-goal2023.1228.9-55.4ContRLGoal Setting=multi-goalGoal Setting=multi-goal2023.1224.7-49.2