ResearchDatasetsD4RL MazeD4RL MazeFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsOffline Reinforcement LearningD4RL Maze maze2d-large v2 (test)156.4Normalized Score12Offline Reinforcement LearningD4RL Maze maze2d-medium v2 (test)11,490Normalized Score12