ResearchTasksFinding an epsilon-optimal policyFinding an epsilon-optimal policyFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedSimulator Model with Stochastic Transitions Completeness assumption——Primary metric0Feb 26, 2026Simulator Model Gap Condition (Realizability assumption)——Primary metric0Feb 26, 2026Online RL with Deterministic Transitions Realizability assumption——Primary metric0Feb 26, 2026Simulator Model Deterministic Transitions (Realizability assumption)——Primary metric0Feb 26, 2026