ResearchDatasetsMuJoCo and Maze2DFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsOffline Reinforcement LearningMuJoCo and Maze2D Final Return v2 (offline pre-training)73.2Hopper (Medium) Return7Offline Reinforcement LearningMuJoCo and Maze2D Step-wise Reward v2 (offline pre-training)66.5Hopper-Medium Score4
Offline Reinforcement LearningMuJoCo and Maze2D Final Return v2 (offline pre-training)73.2Hopper (Medium) Return7
Offline Reinforcement LearningMuJoCo and Maze2D Step-wise Reward v2 (offline pre-training)66.5Hopper-Medium Score4