{"total":223,"rows":[{"id":"2303.05479","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","created":"2023-03-09","cited_by_count":237,"area":"offlinerl"},{"id":"2103.10897","title":"Bilinear Classes: A Structural Framework for Provable Generalization in RL","created":"2021-03-19","cited_by_count":178,"area":null},{"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":"2106.04895","title":"Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning","created":"2021-06-09","cited_by_count":158,"area":"offlinerl"},{"id":"2110.14555","title":"V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL","created":"2021-10-27","cited_by_count":114,"area":null},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110,"area":"offlinerl"},{"id":"2405.21046","title":"Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF","created":"2024-05-31","cited_by_count":106,"area":"alignment"},{"id":"2412.01951","title":"Self-Improvement in Language Models: The Sharpening Mechanism","created":"2024-12-02","cited_by_count":104,"area":"synth"},{"id":"2204.08967","title":"When Is Partially Observable Reinforcement Learning Not Scary?","created":"2022-04-19","cited_by_count":100,"area":null},{"id":"2306.14111","title":"Is RLHF More Difficult than Standard RL?","created":"2023-06-25","cited_by_count":96,"area":"alignment"},{"id":"2210.04157","title":"The Role of Coverage in Online Reinforcement Learning","created":"2022-10-09","cited_by_count":83,"area":"offlinerl"},{"id":"2205.11140","title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation","created":"2022-05-23","cited_by_count":81,"area":null},{"id":"2110.03239","title":"Understanding Domain Randomization for Sim-to-real Transfer","created":"2021-10-07","cited_by_count":80,"area":null},{"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":"2202.00063","title":"Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach","created":"2022-01-31","cited_by_count":51,"area":null},{"id":"2201.11206","title":"Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes","created":"2022-01-26","cited_by_count":49,"area":null},{"id":"2106.03352","title":"The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces","created":"2021-06-07","cited_by_count":48,"area":null},{"id":"2310.14554","title":"Making RL with Preference-based Feedback Efficient via Randomization","created":"2023-10-23","cited_by_count":46,"area":"alignment"},{"id":"2110.03580","title":"A Model Selection Approach for Corruption Robust Reinforcement Learning","created":"2021-10-07","cited_by_count":45,"area":null},{"id":"2107.14702","title":"Towards General Function Approximation in Zero-Sum Markov Games","created":"2021-07-30","cited_by_count":43,"area":null},{"id":"2207.05738","title":"PAC Reinforcement Learning for Predictive State Representations","created":"2022-07-12","cited_by_count":43,"area":null},{"id":"2211.04974","title":"Leveraging Offline Data in Online Reinforcement Learning","created":"2022-11-09","cited_by_count":42,"area":"offlinerl"},{"id":"2202.03983","title":"Provable Reinforcement Learning with a Short-Term Memory","created":"2022-02-08","cited_by_count":40,"area":null},{"id":"2112.03432","title":"First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach","created":"2021-12-07","cited_by_count":38,"area":null},{"id":"2305.04412","title":"Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors","created":"2023-05-08","cited_by_count":36,"area":"driving"},{"id":"2206.12020","title":"Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems","created":"2022-06-24","cited_by_count":35,"area":null},{"id":"2203.13935","title":"Offline Reinforcement Learning Under Value and Density-Ratio Realizability: The Power of Gaps","created":"2022-03-25","cited_by_count":34,"area":"offlinerl"},{"id":"2206.13063","title":"On the Complexity of Adversarial Decision Making","created":"2022-06-27","cited_by_count":33,"area":null},{"id":"2207.02575","title":"Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design","created":"2022-07-06","cited_by_count":33,"area":null},{"id":"2212.05949","title":"Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes","created":"2022-12-12","cited_by_count":33,"area":null},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"id":"2206.07659","title":"Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity","created":"2022-06-15","cited_by_count":32,"area":null},{"id":"2208.10904","title":"A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning","created":"2022-08-23","cited_by_count":31,"area":null},{"id":"2209.15634","title":"A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning","created":"2022-09-30","cited_by_count":31,"area":null},{"id":"2310.14550","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","created":"2023-10-23","cited_by_count":31,"area":"offlinerl"},{"id":"2301.08215","title":"Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient","created":"2023-01-19","cited_by_count":30,"area":null},{"id":"2302.06606","title":"Breaking the Curse of Multiagency: Provably Efficient Decentralized Multi-Agent RL with Function Approximation","created":"2023-02-13","cited_by_count":30,"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":"2105.08024","title":"Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting","created":"2021-05-17","cited_by_count":28,"area":null},{"id":"2206.01315","title":"Sample-Efficient Reinforcement Learning of Partially Observable Markov Games","created":"2022-06-02","cited_by_count":27,"area":null},{"id":"2206.10770","title":"On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL","created":"2022-06-21","cited_by_count":27,"area":null},{"id":"2302.03673","title":"Breaking the Curse of Multiagents in a Large State Space: RL in Markov Games with Independent Linear Function Approximation","created":"2023-02-07","cited_by_count":27,"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":"2206.04282","title":"Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information","created":"2022-06-09","cited_by_count":26,"area":null},{"id":"2404.03578","title":"Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms","created":"2024-04-04","cited_by_count":26,"area":"deeprl"},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2206.04640","title":"Regret Bounds for Information-Directed Reinforcement Learning","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2209.14990","title":"Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms","created":"2022-09-29","cited_by_count":24,"area":null},{"id":"2108.05533","title":"Efficient Local Planning with Linear Function Approximation","created":"2021-08-12","cited_by_count":23,"area":null},{"id":"2402.07198","title":"More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning","created":"2024-02-11","cited_by_count":23,"area":"offlinerl"},{"id":"2304.05889","title":"Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL","created":"2023-04-12","cited_by_count":22,"area":null},{"id":"2502.07460","title":"Logarithmic Regret for Online KL-Regularized Reinforcement Learning","created":"2025-02-11","cited_by_count":22,"area":"alignment"},{"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":"2104.06970","title":"Understanding the Eluder Dimension","created":"2021-04-14","cited_by_count":19,"area":null},{"id":"2110.14798","title":"Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection","created":"2021-10-27","cited_by_count":18,"area":null},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","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":"2302.02571","title":"Offline Learning in Markov Games with General Function Approximation","created":"2023-02-06","cited_by_count":18,"area":"offlinerl"},{"id":"2310.00806","title":"Bayesian Design Principles for Frequentist Sequential Learning","created":"2023-10-01","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":"2301.13087","title":"Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation","created":"2023-01-30","cited_by_count":17,"area":null},{"id":"2310.16173","title":"On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\\epsilon$-Greedy Exploration","created":"2023-10-24","cited_by_count":17,"area":null},{"id":"2203.03684","title":"Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets","created":"2022-03-07","cited_by_count":16,"area":null},{"id":"2210.01907","title":"A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games","created":"2022-10-04","cited_by_count":16,"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":"2307.03997","title":"Efficient Model-Free Exploration in Low-Rank MDPs","created":"2023-07-08","cited_by_count":16,"area":null},{"id":"2403.06323","title":"A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents","created":"2024-03-10","cited_by_count":16,"area":"deeprl"},{"id":"2107.04518","title":"Optimal Gradient-based Algorithms for Non-concave Bandit Optimization","created":"2021-07-09","cited_by_count":15,"area":null},{"id":"2302.01333","title":"Lower Bounds for Learning in Revealing POMDPs","created":"2023-02-02","cited_by_count":15,"area":null},{"id":"2304.08944","title":"Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning","created":"2023-04-18","cited_by_count":15,"area":null},{"id":"2502.20548","title":"$Q\\sharp$: Provably Optimal Distributional RL for LLM Post-Training","created":"2025-02-27","cited_by_count":15,"area":"lr"},{"id":"2303.10859","title":"Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs","created":"2023-03-20","cited_by_count":14,"area":null},{"id":"2305.11283","title":"On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation","created":"2023-05-18","cited_by_count":14,"area":null},{"id":"2306.00212","title":"Provably Efficient Generalized Lagrangian Policy Optimization for Safe Multi-Agent Reinforcement Learning","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2308.14642","title":"Rate-Optimal Policy Optimization for Linear Markov Decision Processes","created":"2023-08-28","cited_by_count":14,"area":null},{"id":"2310.11428","title":"Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression","created":"2023-10-17","cited_by_count":14,"area":null},{"id":"2311.15238","title":"A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation","created":"2023-11-26","cited_by_count":14,"area":null},{"id":"2106.11519","title":"Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations","created":"2021-06-22","cited_by_count":13,"area":null},{"id":"2210.00701","title":"Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2305.11032","title":"Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL","created":"2023-05-18","cited_by_count":13,"area":null},{"id":"2205.15701","title":"Provable General Function Class Representation Learning in Multitask Bandits and MDPs","created":"2022-05-31","cited_by_count":12,"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":"2210.00750","title":"Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient","created":"2022-10-03","cited_by_count":12,"area":"offlinerl"},{"id":"2402.08991","title":"Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption","created":"2024-02-14","cited_by_count":12,"area":"deeprl"},{"id":"2406.12241","title":"More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling","created":"2024-06-18","cited_by_count":12,"area":"deeprl"},{"id":"2209.07376","title":"Understanding Deep Neural Function Approximation in Reinforcement Learning via $\\epsilon$-Greedy Exploration","created":"2022-09-15","cited_by_count":11,"area":null},{"id":"2211.14250","title":"Model-Free Reinforcement Learning with the Decision-Estimation Coefficient","created":"2022-11-25","cited_by_count":11,"area":null},{"id":"2311.08384","title":"Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees","created":"2023-11-14","cited_by_count":11,"area":"offlinerl"},{"id":"2203.08248","title":"Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling","created":"2022-03-15","cited_by_count":10,"area":null},{"id":"2405.17061","title":"Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation","created":"2024-05-27","cited_by_count":10,"area":"deeprl"},{"id":"2510.04088","title":"Offline Reinforcement Learning in Large State Spaces: Algorithms and Guarantees","created":"2025-10-05","cited_by_count":10,"area":"offlinerl"},{"id":"2107.06466","title":"Going Beyond Linear RL: Sample Efficient Neural Function Approximation","created":"2021-07-14","cited_by_count":9,"area":null},{"id":"2210.15598","title":"Provable Sim-to-real Transfer in Continuous Domain with Partial Observations","created":"2022-10-27","cited_by_count":9,"area":null},{"id":"2211.14932","title":"Eluder-based Regret for Stochastic Contextual MDPs","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2302.10796","title":"Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret","created":"2023-02-21","cited_by_count":9,"area":null},{"id":"2302.12456","title":"Logarithmic Switching Cost in Reinforcement Learning beyond Linear MDPs","created":"2023-02-24","cited_by_count":9,"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":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","cited_by_count":9,"area":null},{"id":"2402.05724","title":"Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL","created":"2024-02-08","cited_by_count":9,"area":"deeprl"}],"next_cursor":"100"}