ResearchDatasetsAtari 2600 Q*bertAtari 2600 Q*bertFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsOffline Reinforcement LearningAtari 2600 Q*bert Minari (fixed offline dataset)66Average Episodic Return7
Offline Reinforcement LearningAtari 2600 Q*bert Minari (fixed offline dataset)66Average Episodic Return7