{"total":85,"rows":[{"id":"2405.16436","title":"Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer","created":"2024-05-26","cited_by_count":109,"area":"alignment"},{"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":"2405.19320","title":"Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF","created":"2024-05-29","cited_by_count":73,"area":"alignment"},{"id":"2305.18438","title":"Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism","created":"2023-05-29","cited_by_count":69,"area":"alignment"},{"id":"2203.05804","title":"Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism","created":"2022-03-11","cited_by_count":65,"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":"2203.07368","title":"The Efficacy of Pessimism in Asynchronous Q-Learning","created":"2022-03-14","cited_by_count":42,"area":null},{"id":"2305.10697","title":"The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond","created":"2023-05-18","cited_by_count":36,"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":"2302.11048","title":"Adversarial Model for Offline Reinforcement Learning","created":"2023-02-21","cited_by_count":31,"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":"2310.12955","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","created":"2023-10-19","cited_by_count":24,"area":"offlinerl"},{"id":"2209.08666","title":"Offline Reinforcement Learning with Instrumental Variables in Confounded Markov Decision Processes","created":"2022-09-18","cited_by_count":19,"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":"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":"2307.11352","title":"Model-based Offline Reinforcement Learning with Count-based Conservatism","created":"2023-07-21","cited_by_count":16,"area":"offlinerl"},{"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":"2304.07278","title":"Minimax-Optimal Reward-Agnostic Exploration in Reinforcement Learning","created":"2023-04-14","cited_by_count":15,"area":"offlinerl"},{"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":"2305.19529","title":"Offline Meta Reinforcement Learning with In-Distribution Online Adaptation","created":"2023-05-31","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":"2302.02392","title":"Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage","created":"2023-02-05","cited_by_count":10,"area":"offlinerl"},{"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":"2405.18520","title":"Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL","created":"2024-05-28","cited_by_count":10,"area":"deeprl"},{"id":"2407.14653","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","created":"2024-07-19","cited_by_count":10,"area":"offlinerl"},{"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":"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":"2302.06884","title":"Conservative State Value Estimation for Offline Reinforcement Learning","created":"2023-02-14","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":"2408.16981","title":"The Sample-Communication Complexity Trade-off in Federated Q-Learning","created":"2024-08-30","cited_by_count":9,"area":"deeprl"},{"id":"2305.15546","title":"Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2410.07574","title":"Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition","created":"2024-10-10","cited_by_count":8,"area":"deeprl"},{"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":"2601.19612","title":"Safe Exploration via Policy Priors","created":"2026-01-27","cited_by_count":6,"area":"deeprl"},{"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":"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":"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":"2404.05424","title":"What Are the Odds? Improving the foundations of Statistical Model Checking","created":"2024-04-08","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":"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":"2306.07528","title":"Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective","created":"2023-06-13","cited_by_count":4,"area":"offlinerl"},{"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":"2405.03865","title":"Information-driven Affordance Discovery for Efficient Robotic Manipulation","created":"2024-05-06","cited_by_count":4,"area":null},{"id":"2406.07455","title":"Reinforcement Learning from Human Feedback without Reward Inference: Model-Free Algorithm and Instance-Dependent Analysis","created":"2024-06-11","cited_by_count":4,"area":"alignment"},{"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":"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":"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":"2309.02157","title":"Model-based Offline Policy Optimization with Adversarial Network","created":"2023-09-05","cited_by_count":3,"area":"offlinerl"},{"id":"2310.17245","title":"CROP: Conservative Reward for Model-based Offline Policy Optimization","created":"2023-10-26","cited_by_count":3,"area":"offlinerl"},{"id":"2401.10516","title":"Episodic Reinforcement Learning with Expanded State-reward Space","created":"2024-01-19","cited_by_count":3,"area":"deeprl"},{"id":"2505.18407","title":"KL-regularization Itself is Differentially Private in Bandits and RLHF","created":"2025-05-23","cited_by_count":3,"area":"alignment"},{"id":"2601.13642","title":"Sample Complexity of Average-Reward Q-Learning: From Single-agent to Federated Reinforcement Learning","created":"2026-01-20","cited_by_count":3,"area":"deeprl"},{"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":"2212.08232","title":"Offline Robot Reinforcement Learning with Uncertainty-Guided Human Expert Sampling","created":"2022-12-16","cited_by_count":2,"area":"offlinerl"},{"id":"2505.18447","title":"Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning","created":"2025-05-24","cited_by_count":2,"area":"deeprl"},{"id":"2506.04626","title":"Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning","created":"2025-06-05","cited_by_count":2,"area":"deeprl"},{"id":"2507.14444","title":"Statistical and Algorithmic Foundations of Reinforcement Learning","created":"2025-07-19","cited_by_count":2,"area":"deeprl"},{"id":"2510.01693","title":"PASTA: A Unified Framework for Offline Assortment Learning","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2405.14374","title":"State-Constrained Offline Reinforcement Learning","created":"2024-05-23","cited_by_count":1,"area":"offlinerl"},{"id":"2506.00131","title":"Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimization","created":"2025-05-30","cited_by_count":1,"area":"offlinerl"},{"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":"2205.13950","title":"Non-Markovian policies occupancy measures","created":"2022-05-27","cited_by_count":0,"area":null},{"id":"2401.11380","title":"MoMA: Model-based Mirror Ascent for Offline Reinforcement Learning","created":"2024-01-21","cited_by_count":0,"area":"offlinerl"},{"id":"2403.11841","title":"Pessimistic Causal Reinforcement Learning with Mediators for Confounded Offline Data","created":"2024-03-18","cited_by_count":0,"area":null},{"id":"2604.02438","title":"Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models","created":"2026-04-02","cited_by_count":0,"area":"offlinerl"},{"id":"2604.04218","title":"Sharp asymptotic theory for Q-learning with LDTZ learning rate and its generalization","created":"2026-04-05","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":"2606.20206","title":"Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random","created":"2026-06-18","cited_by_count":0,"area":"offlinerl"},{"id":"2610.18839","title":"Fast Rates for Offline Q-Learning with KL Regularization","created":"2026-10-13","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}