ResearchDatasetsAnt-velFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsReinforcement LearningAnt-vel online downstream setting1.11Normalized Reward6Safe Reinforcement LearningAnt-vel (offline)1.23Normalized Reward6