ResearchDatasetsInverted Double PendulumFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsInverted Double PendulumInverted Double Pendulum100Convergence (%)20Reinforcement LearningInverted Double Pendulum9,359.92Avg Episode Reward18Continuous ControlInverted Double Pendulum0.96Normalized AUC3