{"total":35,"rows":[{"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":"2202.07511","title":"Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets","created":"2022-02-15","cited_by_count":44,"area":null},{"id":"2201.06169","title":"On Well-posedness and Minimax Optimal Rates of Nonparametric Q-function Estimation in Off-policy Evaluation","created":"2022-01-17","cited_by_count":33,"area":null},{"id":"2212.09900","title":"Policy learning \"without\" overlap: Pessimism and generalized empirical Bernstein's inequality","created":"2022-12-19","cited_by_count":32,"area":null},{"id":"2206.05900","title":"Provable Benefit of Multitask Representation Learning in Reinforcement Learning","created":"2022-06-13","cited_by_count":29,"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":"2305.15703","title":"The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning","created":"2023-05-25","cited_by_count":27,"area":null},{"id":"2207.13081","title":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs","created":"2022-07-26","cited_by_count":21,"area":null},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"id":"2205.10671","title":"Pessimism for Offline Linear Contextual Bandits using $\\ell_p$ Confidence Sets","created":"2022-05-21","cited_by_count":18,"area":null},{"id":"2301.13857","title":"Learning in POMDPs is Sample-Efficient with Hindsight Observability","created":"2023-01-31","cited_by_count":18,"area":null},{"id":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2403.11574","title":"Offline Multitask Representation Learning for Reinforcement Learning","created":"2024-03-18","cited_by_count":14,"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":"2209.13075","title":"Off-policy estimation of linear functionals: Non-asymptotic theory for semi-parametric efficiency","created":"2022-09-26","cited_by_count":10,"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":"2210.14420","title":"Optimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach","created":"2022-10-26","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":"2206.00796","title":"Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2501.19300","title":"Offline Learning for Combinatorial Multi-armed Bandits","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2307.08840","title":"Bayesian Safe Policy Learning with Chance Constrained Optimization: Application to Military Security Assessment during the Vietnam War","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2403.07933","title":"Corruption-Robust Offline Two-Player Zero-Sum Markov Games","created":"2024-03-04","cited_by_count":4,"area":null},{"id":"2510.08539","title":"On the optimization dynamics of RLVR: Gradient gap and step size thresholds","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2206.04921","title":"Offline Stochastic Shortest Path: Learning, Evaluation and Towards Optimality","created":"2022-06-10","cited_by_count":3,"area":null},{"id":"2505.13768","title":"Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis","created":"2025-05-19","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":"2411.04138","title":"NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2501.06339","title":"On The Statistical Complexity of Offline Decision-Making","created":"2025-01-10","cited_by_count":2,"area":null},{"id":"2508.20315","title":"Multi-Agent Reinforcement Learning in Intelligent Transportation Systems: A Comprehensive Survey","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2202.00076","title":"Optimal Estimation of Off-Policy Policy Gradient via Double Fitted Iteration","created":"2022-01-31","cited_by_count":1,"area":null},{"id":"2207.14443","title":"A Survey of Learning on Small Data: Generalization, Optimization, and Challenge","created":"2022-07-29","cited_by_count":1,"area":null},{"id":"2310.06243","title":"Sample-Efficient Multi-Agent RL: An Optimization Perspective","created":"2023-10-10","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}],"next_cursor":null}