ResearchTasksPolicy GradientPolicy GradientFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMuJoCo Walker2d (final 20 iterations)Pathwise214Average Return3Feb 26, 2026MuJoCo Hopper (final 20 iterations)Hybrid (λ*)185.9Average Return3Feb 26, 2026MuJoCo HalfCheetah (final 20 iterations)Hybrid (λ*)-524Average Return3Feb 26, 2026