ResearchDatasetsAtari QbertAtari QbertFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsReinforcement LearningAtari Qbert v4 (test)27,234.1Mean Final Score5Offline Reinforcement LearningAtari Qbert 1% DQN-replay v0104.2Gamer-normalized Score5Imitation LearningAtari Qbert v4 (test)12,940Episode Reward2