ResearchTasksCumulative Reward MaximizationCumulative Reward MaximizationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedRay MazeFirst-Explore0.47Mean Cumulative Reward5Feb 26, 2026Dark Treasure RoomsFirst-Explore2Mean Cumulative Reward5Feb 26, 2026Bandits with One Fixed ArmFirst-Explore127.7Mean Cumulative Reward5Feb 26, 2026