ResearchTasksOffline Reinforcement Learning (Navigation)Offline Reinforcement Learning (Navigation)FollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAntMaze umaze-diverse D4RL (ud)DMM94Expert Normalized Return10Feb 26, 2026AntMaze umaze D4RLDMM91Expert Normalized Return10Feb 26, 2026