ResearchDatasetsMuJoCo (D4RL)MuJoCo (D4RL)FollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsOffline Reinforcement LearningMuJoCo (D4RL) medium, medium-replay, medium-expert v291.5HalfCheetah (Medium-Expert)8
Offline Reinforcement LearningMuJoCo (D4RL) medium, medium-replay, medium-expert v291.5HalfCheetah (Medium-Expert)8