ResearchTasksSingle-domain Offline Imitation Learning from Observations (S-off-LfO)FollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedD4RL MuJoCo reward-free v2 (medium, medium-replay, medium-expert)SMODICE54.5Hopper-v2 (m)3Feb 26, 2026
D4RL MuJoCo reward-free v2 (medium, medium-replay, medium-expert)SMODICE54.5Hopper-v2 (m)3Feb 26, 2026