ResearchTasksOffline Preference-Based Reinforcement LearningFor AI assistantsMarkdownContent indexOffline Preference-Based Reinforcement LearningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMeta-WorldOPRL63.2Lever Pull Success Rate5Apr 6, 2026