ResearchTasksSingletask Offline Reinforcement Learning (State-based)Singletask Offline Reinforcement Learning (State-based)FollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedOGBench State-based Singletask Offline v0Value Flows97Success Rate10Mar 4, 2026