{"total":37,"rows":[{"id":"2102.00815","title":"Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms","created":"2021-02-01","cited_by_count":223,"area":null},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161,"area":null},{"id":"2203.02628","title":"Target Network and Truncation Overcome The Deadly Triad in $Q$-Learning","created":"2022-03-05","cited_by_count":31,"area":null},{"id":"2201.03522","title":"When is Offline Two-Player Zero-Sum Markov Game Solvable?","created":"2022-01-10","cited_by_count":28,"area":null},{"id":"2105.03863","title":"Towards Theoretical Understandings of Robust Markov Decision Processes: Sample Complexity and Asymptotics","created":"2021-05-09","cited_by_count":27,"area":null},{"id":"2206.10770","title":"On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL","created":"2022-06-21","cited_by_count":27,"area":null},{"id":"2207.00046","title":"Performative Reinforcement Learning","created":"2022-06-30","cited_by_count":27,"area":null},{"id":"2211.12612","title":"Transfer Learning for Contextual Multi-armed Bandits","created":"2022-11-22","cited_by_count":24,"area":null},{"id":"2211.05311","title":"When is Realizability Sufficient for Off-Policy Reinforcement Learning?","created":"2022-11-10","cited_by_count":17,"area":null},{"id":"2301.13734","title":"Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design","created":"2023-01-31","cited_by_count":14,"area":null},{"id":"2311.18207","title":"Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation","created":"2023-11-30","cited_by_count":13,"area":null},{"id":"2112.12320","title":"Model Selection in Batch Policy Optimization","created":"2021-12-23","cited_by_count":11,"area":null},{"id":"2211.03413","title":"Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification","created":"2022-11-07","cited_by_count":11,"area":null},{"id":"2307.04354","title":"Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data","created":"2023-07-10","cited_by_count":11,"area":null},{"id":"2402.14703","title":"On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation","created":"2024-02-22","cited_by_count":10,"area":null},{"id":"2604.06738","title":"Beyond Pessimism: Offline Learning in KL-regularized Games","created":"2026-04-08","cited_by_count":10,"area":null},{"id":"2306.07818","title":"A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learning","created":"2023-06-13","cited_by_count":9,"area":null},{"id":"2306.13601","title":"Active Coverage for PAC Reinforcement Learning","created":"2023-06-23","cited_by_count":8,"area":null},{"id":"2403.06328","title":"Distributional Successor Features Enable Zero-Shot Policy Optimization","created":"2024-03-10","cited_by_count":8,"area":null},{"id":"2203.04236","title":"A Complete Characterization of Linear Estimators for Offline Policy Evaluation","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2301.06240","title":"Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency","created":"2023-01-16","cited_by_count":6,"area":null},{"id":"2207.08956","title":"Online Learning with Off-Policy Feedback","created":"2022-07-18","cited_by_count":4,"area":null},{"id":"2307.13332","title":"The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation","created":"2023-07-25","cited_by_count":3,"area":null},{"id":"2405.17708","title":"OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators","created":"2024-05-27","cited_by_count":3,"area":null},{"id":"2605.09214","title":"Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2106.09973","title":"The Curse of Passive Data Collection in Batch Reinforcement Learning","created":"2021-06-18","cited_by_count":2,"area":null},{"id":"2407.17910","title":"Causal Deepsets for Off-policy Evaluation under Spatial or Spatio-temporal Interferences","created":"2024-07-25","cited_by_count":2,"area":null},{"id":"2503.04010","title":"Greedy Algorithm for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2512.23805","title":"Fitted Q-Evaluation without Bellman Completeness via Occupancy Weighting","created":"2025-12-29","cited_by_count":2,"area":null},{"id":"2111.11758","title":"The Impact of Data Distribution on Q-learning with Function Approximation","created":"2021-11-23","cited_by_count":1,"area":null},{"id":"2201.02300","title":"Hyperparameter Selection Methods for Fitted Q-Evaluation with Error Guarantee","created":"2022-01-07","cited_by_count":1,"area":null},{"id":"2402.15703","title":"Is Offline Decision Making Possible with Only Few Samples? Reliable Decisions in Data-Starved Bandits via Trust Region Enhancement","created":"2024-02-24","cited_by_count":0,"area":null},{"id":"2410.20017","title":"Off-Policy Selection for Initiating Human-Centric Experimental Design","created":"2024-10-26","cited_by_count":0,"area":null},{"id":"2511.20870","title":"Selecting Belief-State Approximations in Simulators with Latent States","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2605.06474","title":"Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2609.18782","title":"A Convergence Framework for Deep $V$-Learning: Error Propagation and Sharp Action-Gap Bounds","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.04997","title":"Pessimistic Minimax Learning for Public-Private Information Games under Unilateral Coverage","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}