ResearchTasksOffline ControlFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedHeterogeneous Pendulum Rich-Data 600,000 transition stepsAOC-0.6Cumulative Reward7Feb 26, 2026Heterogeneous Pendulum 300,000 transition steps (Mid-Data)AOC-1.25Cumulative Reward7Feb 26, 2026Heterogeneous Pendulum Low-Data 100,000 transition stepsAOC-1.39Cumulative Reward7Feb 26, 2026