{"total":83,"rows":[{"id":"2208.05767","title":"Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity","created":"2022-08-11","cited_by_count":87,"area":"offlinerl"},{"id":"2205.15512","title":"Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game","created":"2022-05-31","cited_by_count":55,"area":"offlinerl"},{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"area":null},{"id":"2305.16589","title":"The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model","created":"2023-05-26","cited_by_count":52,"area":null},{"id":"2305.09659","title":"Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage","created":"2023-05-16","cited_by_count":51,"area":"offlinerl"},{"id":"2307.13586","title":"Settling the Sample Complexity of Online Reinforcement Learning","created":"2023-07-25","cited_by_count":45,"area":null},{"id":"2206.00159","title":"Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus","created":"2022-06-01","cited_by_count":30,"area":"offlinerl"},{"id":"2311.12996","title":"RLIF: Interactive Imitation Learning as Reinforcement Learning","created":"2023-11-21","cited_by_count":30,"area":"offlinerl"},{"id":"2211.00716","title":"Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian","created":"2022-11-01","cited_by_count":29,"area":"offlinerl"},{"id":"2305.18420","title":"Sample Complexity of Variance-reduced Distributionally Robust Q-learning","created":"2023-05-28","cited_by_count":29,"area":null},{"id":"2310.12955","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","created":"2023-10-19","cited_by_count":24,"area":"offlinerl"},{"id":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21,"area":"lr"},{"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":"2302.02571","title":"Offline Learning in Markov Games with General Function Approximation","created":"2023-02-06","cited_by_count":18,"area":"offlinerl"},{"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":"2305.10282","title":"Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning","created":"2023-05-17","cited_by_count":16,"area":"offlinerl"},{"id":"2305.19001","title":"High-probability sample complexities for policy evaluation with linear function approximation","created":"2023-05-30","cited_by_count":16,"area":null},{"id":"2406.04274","title":"Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models","created":"2024-06-06","cited_by_count":16,"area":"alignment"},{"id":"2208.10458","title":"Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model","created":"2022-08-22","cited_by_count":15,"area":null},{"id":"2212.13861","title":"Offline Reinforcement Learning via Linear-Programming with Error-Bound Induced Constraints","created":"2022-12-28","cited_by_count":15,"area":"offlinerl"},{"id":"2304.07278","title":"Minimax-Optimal Reward-Agnostic Exploration in Reinforcement Learning","created":"2023-04-14","cited_by_count":15,"area":"offlinerl"},{"id":"2310.08833","title":"Optimal Sample Complexity for Average Reward Markov Decision Processes","created":"2023-10-13","cited_by_count":15,"area":null},{"id":"2403.12946","title":"Sample Complexity of Offline Distributionally Robust Linear Markov Decision Processes","created":"2024-03-19","cited_by_count":14,"area":"offlinerl"},{"id":"2206.00177","title":"On Gap-dependent Bounds for Offline Reinforcement Learning","created":"2022-06-01","cited_by_count":13,"area":"offlinerl"},{"id":"2206.06426","title":"Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward","created":"2022-06-13","cited_by_count":13,"area":"offlinerl"},{"id":"2307.12975","title":"Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems","created":"2023-07-24","cited_by_count":13,"area":"alignment"},{"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":"2210.00750","title":"Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient","created":"2022-10-03","cited_by_count":12,"area":"offlinerl"},{"id":"2310.18434","title":"Bridging Distributionally Robust Learning and Offline RL: An Approach to Mitigate Distribution Shift and Partial Data Coverage","created":"2023-10-27","cited_by_count":12,"area":"offlinerl"},{"id":"2402.05876","title":"Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices","created":"2024-02-08","cited_by_count":11,"area":"offlinerl"},{"id":"2510.24700","title":"Greedy Sampling Is Provably Efficient for RLHF","created":"2025-10-28","cited_by_count":11,"area":"alignment"},{"id":"2309.00591","title":"Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms","created":"2023-09-01","cited_by_count":10,"area":null},{"id":"2502.06051","title":"Towards a Sharp Analysis of Offline Policy Learning for $f$-Divergence-Regularized Contextual Bandits","created":"2025-02-09","cited_by_count":10,"area":"offlinerl"},{"id":"2604.06738","title":"Beyond Pessimism: Offline Learning in KL-regularized Games","created":"2026-04-08","cited_by_count":10,"area":null},{"id":"2208.11040","title":"Strategic Decision-Making in the Presence of Information Asymmetry: Provably Efficient RL with Algorithmic Instruments","created":"2022-08-23","cited_by_count":9,"area":"offlinerl"},{"id":"2310.01380","title":"Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning","created":"2023-10-02","cited_by_count":9,"area":"offlinerl"},{"id":"2401.08819","title":"Learning from Sparse Offline Datasets via Conservative Density Estimation","created":"2024-01-16","cited_by_count":9,"area":"offlinerl"},{"id":"2505.15694","title":"A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO","created":"2025-05-21","cited_by_count":8,"area":"alignment"},{"id":"2305.03360","title":"A Survey on Offline Model-Based Reinforcement Learning","created":"2023-05-05","cited_by_count":7,"area":"offlinerl"},{"id":"2412.08794","title":"Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning","created":"2024-12-11","cited_by_count":7,"area":"offlinerl"},{"id":"2302.07477","title":"Optimal Sample Complexity of Stable Discounted Markov Decision Processes","created":"2023-02-15","cited_by_count":6,"area":null},{"id":"2407.07631","title":"Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning","created":"2024-07-10","cited_by_count":6,"area":"offlinerl"},{"id":"2408.04526","title":"Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs","created":"2024-08-08","cited_by_count":6,"area":"offlinerl"},{"id":"2508.03768","title":"ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning","created":"2025-08-05","cited_by_count":6,"area":"deeprl"},{"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":"2207.06147","title":"A Near-Optimal Primal-Dual Method for Off-Policy Learning in CMDP","created":"2022-07-13","cited_by_count":5,"area":null},{"id":"2211.07092","title":"Offline Estimation of Controlled Markov Chains: Minimaxity and Sample Complexity","created":"2022-11-14","cited_by_count":5,"area":null},{"id":"2302.03770","title":"Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability","created":"2023-02-07","cited_by_count":5,"area":"offlinerl"},{"id":"2501.19300","title":"Offline Learning for Combinatorial Multi-armed Bandits","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2506.00286","title":"Recursive Entropic Risk Optimization in Discounted MDPs: Sample Complexity Bounds with a Generative Model","created":"2025-05-30","cited_by_count":5,"area":"deeprl"},{"id":"2605.00264","title":"Pessimism-Free Offline Learning in General-Sum Games via KL Regularization","created":"2026-04-30","cited_by_count":5,"area":"offlinerl"},{"id":"2303.04268","title":"On the Sample Complexity of Vanilla Model-Based Offline Reinforcement Learning with Dependent Samples","created":"2023-03-07","cited_by_count":4,"area":"offlinerl"},{"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":"2206.04921","title":"Offline Stochastic Shortest Path: Learning, Evaluation and Towards Optimality","created":"2022-06-10","cited_by_count":3,"area":null},{"id":"2305.13289","title":"Achieving the Asymptotically Optimal Sample Complexity of Offline Reinforcement Learning: A DRO-Based Approach","created":"2023-05-22","cited_by_count":3,"area":"offlinerl"},{"id":"2306.08364","title":"Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources","created":"2023-06-14","cited_by_count":3,"area":"offlinerl"},{"id":"2409.02747","title":"Tractable Offline Learning of Regular Decision Processes","created":"2024-09-04","cited_by_count":3,"area":"offlinerl"},{"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":"2506.20904","title":"Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL","created":"2025-06-26","cited_by_count":3,"area":"offlinerl"},{"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":"2405.13755","title":"Offline RL via Feature-Occupancy Gradient Ascent","created":"2024-05-22","cited_by_count":2,"area":"offlinerl"},{"id":"2405.19189","title":"DyDiff: Long-Horizon Rollout via Dynamics Diffusion for Offline Reinforcement Learning","created":"2024-05-29","cited_by_count":2,"area":"diffusion"},{"id":"2502.16195","title":"Statistical Inference in Reinforcement Learning: A Selective Survey","created":"2025-02-22","cited_by_count":2,"area":"deeprl"},{"id":"2503.12283","title":"Towards Optimal Offline Reinforcement Learning","created":"2025-03-15","cited_by_count":2,"area":"offlinerl"},{"id":"2505.15342","title":"Policy Testing in Markov Decision Processes","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2505.20781","title":"STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation","created":"2025-05-27","cited_by_count":2,"area":"diffusion"},{"id":"2507.14444","title":"Statistical and Algorithmic Foundations of Reinforcement Learning","created":"2025-07-19","cited_by_count":2,"area":"deeprl"},{"id":"2508.01517","title":"Central Limit Theorems for Transition Probabilities of Controlled Markov Chains","created":"2025-08-02","cited_by_count":1,"area":null},{"id":"2512.04341","title":"Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism","created":"2025-12-04","cited_by_count":1,"area":"offlinerl"},{"id":"2602.16363","title":"Improved Bounds for Reward-Agnostic and Reward-Free Exploration","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2605.03393","title":"Adaptive Estimation and Optimal Control in Offline Contextual MDPs without Stationarity","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2605.21763","title":"On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents","created":"2026-05-20","cited_by_count":1,"area":"deeprl"},{"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":"2406.01378","title":"A Fast Convergence Theory for Offline Decision Making","created":"2024-06-03","cited_by_count":0,"area":"offlinerl"},{"id":"2406.04841","title":"Primitive Agentic First-Order Optimization","created":"2024-06-07","cited_by_count":0,"area":"agents"},{"id":"2502.00850","title":"Dual Alignment Maximin Optimization for Offline Model-based RL","created":"2025-02-02","cited_by_count":0,"area":"offlinerl"},{"id":"2505.22442","title":"Fully Offline Reinforcement Learning","created":"2025-05-28","cited_by_count":0,"area":"offlinerl"},{"id":"2510.03912","title":"Generalized Fitted Q-Iteration with Clustered Data","created":"2025-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2510.19528","title":"Learning Upper Lower Value Envelopes to Shape Online RL: A Principled Approach","created":"2025-10-22","cited_by_count":0,"area":"deeprl"},{"id":"2605.07218","title":"Improved Model-based Reinforcement Learning with Smooth Kernels","created":"2026-05-08","cited_by_count":0,"area":"deeprl"},{"id":"2605.25114","title":"Counterfactually Safe Reinforcement Learning","created":"2026-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2606.20356","title":"Robust $Q$-learning for mean-field control under Wasserstein uncertainty in common noise","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2610.06931","title":"Near-Optimal Sample Complexity for Recursive Entropic Risk Reinforcement Learning with a Generative Model","created":"2026-10-03","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}