{"total":20,"rows":[{"id":"2108.02717","title":"Beyond No Regret: Instance-Dependent PAC Reinforcement Learning","created":"2021-08-05","cited_by_count":41,"area":null},{"id":"2207.02575","title":"Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design","created":"2022-07-06","cited_by_count":33,"area":null},{"id":"2203.09251","title":"Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs","created":"2022-03-17","cited_by_count":17,"area":null},{"id":"2108.05439","title":"Gap-Dependent Unsupervised Exploration for Reinforcement Learning","created":"2021-08-11","cited_by_count":10,"area":null},{"id":"2311.05638","title":"Towards Instance-Optimality in Online PAC Reinforcement Learning","created":"2023-10-31","cited_by_count":7,"area":null},{"id":"2502.02516","title":"Adaptive Exploration for Multi-Reward Multi-Policy Evaluation","created":"2025-02-04","cited_by_count":6,"area":null},{"id":"2303.04651","title":"MCTS-GEB: Monte Carlo Tree Search is a Good E-graph Builder","created":"2023-03-08","cited_by_count":5,"area":null},{"id":"2208.05633","title":"Best Policy Identification in Linear MDPs","created":"2022-08-11","cited_by_count":4,"area":null},{"id":"2502.02859","title":"Gap-Dependent Bounds for Federated $Q$-learning","created":"2025-02-05","cited_by_count":4,"area":null},{"id":"2503.07824","title":"Pure Exploration with Feedback Graphs","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2506.06521","title":"Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs","created":"2025-06-06","cited_by_count":4,"area":null},{"id":"2310.13393","title":"Optimal Best Arm Identification with Fixed Confidence in Restless Bandits","created":"2023-10-20","cited_by_count":3,"area":null},{"id":"2408.17313","title":"Fair Best Arm Identification with Fixed Confidence","created":"2024-08-30","cited_by_count":3,"area":null},{"id":"2505.15342","title":"Policy Testing in Markov Decision Processes","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2602.17587","title":"Asymptotically Optimal Sequential Testing with Markovian Data","created":"2026-02-19","cited_by_count":2,"area":null},{"id":"2205.14202","title":"Robust Phi-Divergence MDPs","created":"2022-05-27","cited_by_count":1,"area":null},{"id":"2606.25170","title":"Minimax PAC Bounds for Learning in Exogenous Contextual MDPs","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2608.21995","title":"Variance Driven Exploration: A Provable and Efficient Methodology for Pure Exploration in Highly Stochastic Environments","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2609.30360","title":"Cost-Aware Best-LLM Identification using Dueling Feedback","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.36741","title":"Distinguish or Homogenize: Last-Chance Policy Identification and Risk-Budgeted Recovery under Irreversible Resource Depletion","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}