ResearchTasksContinuous Control (Positive Reward)Continuous Control (Positive Reward)FollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedReacher PybulletImplementation [20]18.7Mean Return6Feb 26, 2026Pendulum PybulletImplementation [21]9,043.3Return6Feb 26, 2026Pendulum MujocoImplementation [21]9,358.4Return6Feb 26, 2026