ResearchTasksOffline Reinforcement Learning (Robotic Manipulation)Offline Reinforcement Learning (Robotic Manipulation)FollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedD4RL AdroitBFQ82Score (pen-human-v1)12Jun 11, 2026Franka Kitchen partial D4RL (pt)DMM80.5Expert Normalized Return10Feb 26, 2026