{"total":72,"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":"2208.05129","title":"Robust Reinforcement Learning using Offline Data","created":"2022-08-10","cited_by_count":96,"area":null},{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95,"area":null},{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"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":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"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":"2305.18258","title":"Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration","created":"2023-05-29","cited_by_count":20,"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":"2301.03377","title":"Machine Learning for Large-Scale Optimization in 6G Wireless Networks","created":"2023-01-03","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":"2302.02252","title":"Reinforcement Learning in Low-Rank MDPs with Density Features","created":"2023-02-04","cited_by_count":18,"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":"2306.11626","title":"Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity","created":"2023-06-20","cited_by_count":17,"area":null},{"id":"2310.03173","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","created":"2023-10-04","cited_by_count":17,"area":null},{"id":"2402.04647","title":"Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference","created":"2024-02-07","cited_by_count":14,"area":null},{"id":"2310.19308","title":"Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning","created":"2023-10-30","cited_by_count":13,"area":null},{"id":"2206.01588","title":"Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Games","created":"2022-06-03","cited_by_count":12,"area":null},{"id":"2206.02887","title":"Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks","created":"2022-06-06","cited_by_count":12,"area":null},{"id":"2209.09845","title":"Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL","created":"2022-09-20","cited_by_count":12,"area":null},{"id":"2303.00694","title":"The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms","created":"2023-03-01","cited_by_count":12,"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":"2401.05442","title":"Functional Graphical Models: Structure Enables Offline Data-Driven Optimization","created":"2024-01-08","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":"2310.08089","title":"Learning Regularized Monotone Graphon Mean-Field Games","created":"2023-10-12","cited_by_count":9,"area":null},{"id":"2210.15543","title":"Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions","created":"2022-10-27","cited_by_count":8,"area":null},{"id":"2303.05606","title":"Variance-aware robust reinforcement learning with linear function approximation under heavy-tailed rewards","created":"2023-03-09","cited_by_count":8,"area":null},{"id":"2306.00324","title":"Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning","created":"2023-06-01","cited_by_count":8,"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":"2307.00405","title":"Provably Efficient UCB-type Algorithms For Learning Predictive State Representations","created":"2023-07-01","cited_by_count":6,"area":null},{"id":"2309.13278","title":"Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework","created":"2023-09-23","cited_by_count":6,"area":null},{"id":"2406.00317","title":"Combining Experimental and Historical Data for Policy Evaluation","created":"2024-06-01","cited_by_count":6,"area":null},{"id":"2605.13025","title":"Offline Two-Player Zero-Sum Markov Games with KL Regularization","created":"2026-05-13","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":"2403.09701","title":"A Natural Extension To Online Algorithms For Hybrid RL With Limited Coverage","created":"2024-03-07","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":"2207.08956","title":"Online Learning with Off-Policy Feedback","created":"2022-07-18","cited_by_count":4,"area":null},{"id":"2305.04819","title":"Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning","created":"2023-05-08","cited_by_count":4,"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":"2502.06777","title":"Learning an Optimal Assortment Policy under Observational Data","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2605.02141","title":"On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization","created":"2026-05-04","cited_by_count":4,"area":null},{"id":"2205.12418","title":"Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret","created":"2022-05-25","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":"2106.09973","title":"The Curse of Passive Data Collection in Batch Reinforcement Learning","created":"2021-06-18","cited_by_count":2,"area":null},{"id":"2206.02593","title":"Pessimistic Off-Policy Optimization for Learning to Rank","created":"2022-06-06","cited_by_count":2,"area":null},{"id":"2303.11187","title":"A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observations","created":"2023-03-20","cited_by_count":2,"area":null},{"id":"2501.05591","title":"Session-Level Dynamic Ad Load Optimization using Offline Robust Reinforcement Learning","created":"2025-01-09","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":"2512.23805","title":"Fitted Q-Evaluation without Bellman Completeness via Occupancy Weighting","created":"2025-12-29","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":"2210.13396","title":"Offline congestion games: How feedback type affects data coverage requirement","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2302.05534","title":"Robust Knowledge Transfer in Tiered Reinforcement Learning","created":"2023-02-10","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":"2408.07753","title":"How to Solve Contextual Goal-Oriented Problems with Offline Datasets?","created":"2024-08-14","cited_by_count":1,"area":null},{"id":"2505.17506","title":"Offline Constrained Reinforcement Learning under Partial Data Coverage","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2306.01237","title":"Bayesian Regret Minimization in Offline Bandits","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2311.18725","title":"AI in Pharma for Personalized Sequential Decision-Making: Methods, Applications and Opportunities","created":"2023-11-30","cited_by_count":0,"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":"2507.00851","title":"Aligning Learning and Endogenous Decision-Making","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2604.02349","title":"OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration","created":"2026-02-19","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}