{"total":65,"rows":[{"id":"2312.11456","title":"Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint","created":"2023-12-18","cited_by_count":350,"area":"alignment"},{"id":"2206.02829","title":"RORL: Robust Offline Reinforcement Learning via Conservative Smoothing","created":"2022-06-06","cited_by_count":84,"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":"2307.13586","title":"Settling the Sample Complexity of Online Reinforcement Learning","created":"2023-07-25","cited_by_count":45,"area":null},{"id":"2203.07368","title":"The Efficacy of Pessimism in Asynchronous Q-Learning","created":"2022-03-14","cited_by_count":42,"area":null},{"id":"2211.04974","title":"Leveraging Offline Data in Online Reinforcement Learning","created":"2022-11-09","cited_by_count":42,"area":"offlinerl"},{"id":"2209.06620","title":"Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation","created":"2022-09-14","cited_by_count":32,"area":"offlinerl"},{"id":"2206.05900","title":"Provable Benefit of Multitask Representation Learning in Reinforcement Learning","created":"2022-06-13","cited_by_count":29,"area":null},{"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":"2205.13589","title":"Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes","created":"2022-05-26","cited_by_count":26,"area":"offlinerl"},{"id":"2211.13208","title":"On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation","created":"2022-11-23","cited_by_count":22,"area":"offlinerl"},{"id":"2206.00810","title":"Offline Reinforcement Learning with Differential Privacy","created":"2022-06-02","cited_by_count":20,"area":"offlinerl"},{"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":"2403.09621","title":"Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning","created":"2024-03-14","cited_by_count":18,"area":"offlinerl"},{"id":"2212.04680","title":"Near-Optimal Differentially Private Reinforcement Learning","created":"2022-12-09","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":"2211.15956","title":"Offline Reinforcement Learning with Closed-Form Policy Improvement Operators","created":"2022-11-29","cited_by_count":14,"area":"offlinerl"},{"id":"2403.11574","title":"Offline Multitask Representation Learning for Reinforcement Learning","created":"2024-03-18","cited_by_count":14,"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":"2502.17515","title":"Towards User-level Private Reinforcement Learning with Human Feedback","created":"2025-02-22","cited_by_count":14,"area":"alignment"},{"id":"2206.06426","title":"Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward","created":"2022-06-13","cited_by_count":13,"area":"offlinerl"},{"id":"2301.12714","title":"Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning","created":"2023-01-30","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":"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":"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":"2310.19733","title":"Differentially Private Reward Estimation with Preference Feedback","created":"2023-10-30","cited_by_count":12,"area":"alignment"},{"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":"2203.12786","title":"Bellman Residual Orthogonalization for Offline Reinforcement Learning","created":"2022-03-24","cited_by_count":10,"area":"offlinerl"},{"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":"2310.01380","title":"Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning","created":"2023-10-02","cited_by_count":9,"area":"offlinerl"},{"id":"2212.07486","title":"Scaling Marginalized Importance Sampling to High-Dimensional State-Spaces via State Abstraction","created":"2022-12-14","cited_by_count":7,"area":null},{"id":"2405.11206","title":"Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses","created":"2024-05-18","cited_by_count":7,"area":"offlinerl"},{"id":"2406.00317","title":"Combining Experimental and Historical Data for Policy Evaluation","created":"2024-06-01","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":"2305.13185","title":"Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice","created":"2023-05-22","cited_by_count":4,"area":null},{"id":"2406.11686","title":"The Role of Inherent Bellman Error in Offline Reinforcement Learning with Linear Function Approximation","created":"2024-06-17","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":"2302.12780","title":"VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation","created":"2023-02-24","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":"2310.18919","title":"Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation","created":"2023-10-29","cited_by_count":3,"area":null},{"id":"2401.05233","title":"Taming \"data-hungry\" reinforcement learning? Stability in continuous state-action spaces","created":"2024-01-10","cited_by_count":3,"area":"deeprl"},{"id":"2503.07988","title":"Provable Zero-Shot Generalization in Offline Reinforcement Learning","created":"2025-03-11","cited_by_count":3,"area":"offlinerl"},{"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":"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":"2408.12307","title":"Leveraging Unlabeled Data Sharing through Kernel Function Approximation in Offline Reinforcement Learning","created":"2024-08-22","cited_by_count":2,"area":"offlinerl"},{"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":"2507.14444","title":"Statistical and Algorithmic Foundations of Reinforcement Learning","created":"2025-07-19","cited_by_count":2,"area":"deeprl"},{"id":"2406.01838","title":"Learning the Target Network in Function Space","created":"2024-06-03","cited_by_count":1,"area":"deeprl"},{"id":"2406.12205","title":"On the Exponential Convergence for Offline RLHF with Pairwise Comparisons","created":"2024-06-18","cited_by_count":1,"area":"alignment"},{"id":"2601.19030","title":"A Unifying View of Coverage in Linear Off-Policy Evaluation","created":"2026-01-26","cited_by_count":1,"area":"deeprl"},{"id":"2605.00654","title":"Reinforcement Learning with Markov Risk Measures and Multipattern Risk Approximation","created":"2026-05-01","cited_by_count":1,"area":"deeprl"},{"id":"2306.14063","title":"Offline Policy Evaluation for Reinforcement Learning with Adaptively Collected Data","created":"2023-06-24","cited_by_count":0,"area":"offlinerl"},{"id":"2309.16631","title":"Robust Offline Reinforcement Learning -- Certify the Confidence Interval","created":"2023-09-28","cited_by_count":0,"area":"offlinerl"},{"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":"2504.09339","title":"Towards Optimal Differentially Private Regret Bounds in Linear MDPs","created":"2025-04-12","cited_by_count":0,"area":"deeprl"},{"id":"2509.22964","title":"Functional Critics Are Essential for Actor-Critic: From Off-Policy Stability to Efficient Exploration","created":"2025-09-26","cited_by_count":0,"area":"deeprl"},{"id":"2604.11994","title":"Offline-Online Reinforcement Learning for Linear Mixture MDPs","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.13966","title":"Provably Efficient Offline-to-Online Value Adaptation with General Function Approximation","created":"2026-04-15","cited_by_count":0,"area":"offlinerl"},{"id":"2609.07998","title":"Mini-Batch Risk-Averse Deep Q-Learning: A Robot Navigation Case Study","created":"2026-09-07","cited_by_count":0,"area":"deeprl"},{"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}