ResearchDatasetsStochastic GridWorldStochastic GridWorldFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsOptimal policy selectionStochastic Gridworld (S=16, A=4)100PCS28Reinforcement LearningStochastic GridWorld (20% slip probability) (test)85Success Rate5