{"total":106,"rows":[{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279,"area":"offlinerl"},{"id":"2102.00815","title":"Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms","created":"2021-02-01","cited_by_count":223,"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":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106,"area":null},{"id":"2202.13890","title":"Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity","created":"2022-02-28","cited_by_count":85,"area":"offlinerl"},{"id":"2110.04184","title":"When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?","created":"2021-10-08","cited_by_count":67,"area":null},{"id":"2505.16984","title":"UFT: Unifying Supervised and Reinforcement Fine-Tuning","created":"2025-05-22","cited_by_count":59,"area":"lr"},{"id":"2102.01748","title":"Near-Optimal Offline Reinforcement Learning via Double Variance Reduction","created":"2021-02-02","cited_by_count":56,"area":"offlinerl"},{"id":"2110.04645","title":"Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning","created":"2021-10-09","cited_by_count":53,"area":null},{"id":"2103.01312","title":"UCB Momentum Q-learning: Correcting the bias without forgetting","created":"2021-03-01","cited_by_count":46,"area":null},{"id":"2307.13586","title":"Settling the Sample Complexity of Online Reinforcement Learning","created":"2023-07-25","cited_by_count":45,"area":null},{"id":"2303.08059","title":"Fast Rates for Maximum Entropy Exploration","created":"2023-03-14","cited_by_count":33,"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":"2106.02847","title":"Navigating to the Best Policy in Markov Decision Processes","created":"2021-06-05","cited_by_count":29,"area":null},{"id":"2207.06272","title":"Hindsight Learning for MDPs with Exogenous Inputs","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2402.15776","title":"Truly No-Regret Learning in Constrained MDPs","created":"2024-02-24","cited_by_count":23,"area":"deeprl"},{"id":"2102.03192","title":"Provably Efficient Algorithms for Multi-Objective Competitive RL","created":"2021-02-05","cited_by_count":22,"area":null},{"id":"2205.07704","title":"From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses","created":"2022-05-16","cited_by_count":22,"area":null},{"id":"2304.12966","title":"Towards Theoretical Understanding of Inverse Reinforcement Learning","created":"2023-04-25","cited_by_count":21,"area":"offlinerl"},{"id":"2301.13446","title":"Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments","created":"2023-01-31","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":"2203.09251","title":"Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs","created":"2022-03-17","cited_by_count":17,"area":null},{"id":"2207.05852","title":"Optimistic PAC Reinforcement Learning: the Instance-Dependent View","created":"2022-07-12","cited_by_count":17,"area":null},{"id":"2210.14051","title":"Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds","created":"2022-10-25","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":"2102.09703","title":"Near-Optimal Randomized Exploration for Tabular Markov Decision Processes","created":"2021-02-19","cited_by_count":15,"area":null},{"id":"2106.13013","title":"A Fully Problem-Dependent Regret Lower Bound for Finite-Horizon MDPs","created":"2021-06-24","cited_by_count":15,"area":null},{"id":"2301.12601","title":"Regret Bounds for Markov Decision Processes with Recursive Optimized Certainty Equivalents","created":"2023-01-30","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":"2304.07278","title":"Minimax-Optimal Reward-Agnostic Exploration in Reinforcement Learning","created":"2023-04-14","cited_by_count":15,"area":"offlinerl"},{"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":"2106.11519","title":"Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations","created":"2021-06-22","cited_by_count":13,"area":null},{"id":"2112.10935","title":"Nearly Optimal Policy Optimization with Stable at Any Time Guarantee","created":"2021-12-21","cited_by_count":13,"area":null},{"id":"2310.00817","title":"Learning to Make Adherence-Aware Advice","created":"2023-10-01","cited_by_count":13,"area":null},{"id":"2102.12948","title":"Provably Breaking the Quadratic Error Compounding Barrier in Imitation Learning, Optimally","created":"2021-02-25","cited_by_count":12,"area":"offlinerl"},{"id":"2210.02087","title":"Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration and Planning","created":"2022-10-05","cited_by_count":12,"area":null},{"id":"2410.05117","title":"Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability","created":"2024-10-07","cited_by_count":12,"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":"2211.14250","title":"Model-Free Reinforcement Learning with the Decision-Estimation Coefficient","created":"2022-11-25","cited_by_count":11,"area":null},{"id":"2311.13294","title":"Probabilistic Inference in Reinforcement Learning Done Right","created":"2023-11-22","cited_by_count":11,"area":null},{"id":"2206.14057","title":"Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL","created":"2022-06-28","cited_by_count":10,"area":null},{"id":"2106.11692","title":"A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning","created":"2021-06-22","cited_by_count":9,"area":null},{"id":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","cited_by_count":9,"area":null},{"id":"2403.13281","title":"Waypoint-Based Reinforcement Learning for Robot Manipulation Tasks","created":"2024-03-20","cited_by_count":9,"area":"deeprl"},{"id":"2407.13743","title":"Optimistic Q-learning for average reward and episodic reinforcement learning","created":"2024-07-18","cited_by_count":9,"area":"deeprl"},{"id":"2306.02399","title":"Regret Bounds for Risk-sensitive Reinforcement Learning with Lipschitz Dynamic Risk Measures","created":"2023-06-04","cited_by_count":8,"area":null},{"id":"2308.01490","title":"Minimax Optimal Q Learning with Nearest Neighbors","created":"2023-08-03","cited_by_count":8,"area":null},{"id":"2406.02258","title":"Reinforcement Learning with Lookahead Information","created":"2024-06-04","cited_by_count":8,"area":"deeprl"},{"id":"2411.03810","title":"Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data","created":"2024-11-06","cited_by_count":8,"area":"deeprl"},{"id":"2311.05638","title":"Towards Instance-Optimality in Online PAC Reinforcement Learning","created":"2023-10-31","cited_by_count":7,"area":null},{"id":"2410.08870","title":"Can we hop in general? A discussion of benchmark selection and design using the Hopper environment","created":"2024-10-11","cited_by_count":7,"area":"deeprl"},{"id":"2403.10738","title":"Horizon-Free Regret for Linear Markov Decision Processes","created":"2024-03-15","cited_by_count":6,"area":"deeprl"},{"id":"2403.11637","title":"The Value of Reward Lookahead in Reinforcement Learning","created":"2024-03-18","cited_by_count":6,"area":"deeprl"},{"id":"2508.03768","title":"ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning","created":"2025-08-05","cited_by_count":6,"area":"deeprl"},{"id":"2110.09507","title":"Provable Hierarchy-Based Meta-Reinforcement Learning","created":"2021-10-18","cited_by_count":5,"area":null},{"id":"2111.07615","title":"Optimism and Delays in Episodic Reinforcement Learning","created":"2021-11-15","cited_by_count":5,"area":null},{"id":"2210.00832","title":"Square-root regret bounds for continuous-time episodic Markov decision processes","created":"2022-10-03","cited_by_count":5,"area":null},{"id":"2306.06265","title":"Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2406.03812","title":"How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach","created":"2024-06-06","cited_by_count":5,"area":"offlinerl"},{"id":"2111.12045","title":"Adaptive Multi-Goal Exploration","created":"2021-11-23","cited_by_count":4,"area":null},{"id":"2201.13170","title":"Cooperative Online Learning in Stochastic and Adversarial MDPs","created":"2022-01-31","cited_by_count":4,"area":null},{"id":"2208.05633","title":"Best Policy Identification in Linear MDPs","created":"2022-08-11","cited_by_count":4,"area":null},{"id":"2210.11604","title":"Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2306.01121","title":"Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards","created":"2023-06-01","cited_by_count":4,"area":null},{"id":"2306.01243","title":"Efficient Reinforcement Learning with Impaired Observability: Learning to Act with Delayed and Missing State Observations","created":"2023-06-02","cited_by_count":4,"area":null},{"id":"2311.07876","title":"Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback","created":"2023-11-14","cited_by_count":4,"area":null},{"id":"2312.12558","title":"Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge","created":"2023-12-19","cited_by_count":4,"area":null},{"id":"2502.02859","title":"Gap-Dependent Bounds for Federated $Q$-learning","created":"2025-02-05","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":"2312.08369","title":"The Effective Horizon Explains Deep RL Performance in Stochastic Environments","created":"2023-12-13","cited_by_count":3,"area":null},{"id":"2411.00707","title":"Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2602.15012","title":"Cold-Start Personalization via Training-Free Priors from Structured World Models","created":"2026-02-16","cited_by_count":3,"area":"wm"},{"id":"2202.07995","title":"Branching Reinforcement Learning","created":"2022-02-16","cited_by_count":2,"area":null},{"id":"2205.10729","title":"Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path","created":"2022-05-22","cited_by_count":2,"area":null},{"id":"2503.00810","title":"Minimax Optimal Reinforcement Learning with Quasi-Optimism","created":"2025-03-02","cited_by_count":2,"area":"deeprl"},{"id":"2504.05585","title":"TW-CRL: Time-Weighted Contrastive Reward Learning for Efficient Inverse Reinforcement Learning","created":"2025-04-08","cited_by_count":2,"area":"offlinerl"},{"id":"2506.24005","title":"Provably Efficient and Agile Randomized Q-Learning","created":"2025-06-30","cited_by_count":2,"area":"deeprl"},{"id":"2507.11706","title":"Reinforcement Learning from Adversarial Preferences in Tabular MDPs","created":"2025-07-15","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":"2405.16739","title":"Oracle-Efficient Reinforcement Learning for Max Value Ensembles","created":"2024-05-27","cited_by_count":1,"area":"deeprl"},{"id":"2410.02994","title":"Finite-Sample Analysis of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning","created":"2024-10-03","cited_by_count":1,"area":"deeprl"},{"id":"2411.11647","title":"Near-Optimal Reinforcement Learning with Shuffle Differential Privacy","created":"2024-11-18","cited_by_count":1,"area":"deeprl"},{"id":"2502.17370","title":"A Refined Analysis of UCBVI","created":"2025-02-24","cited_by_count":1,"area":null},{"id":"2602.15076","title":"Near-Optimal Sample Complexity for Online Constrained MDPs","created":"2026-02-16","cited_by_count":1,"area":"deeprl"},{"id":"2602.16363","title":"Improved Bounds for Reward-Agnostic and Reward-Free Exploration","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2301.04268","title":"Adversarial Online Multi-Task Reinforcement Learning","created":"2023-01-11","cited_by_count":0,"area":null},{"id":"2309.15395","title":"Model-Free, Regret-Optimal Best Policy Identification in Online CMDPs","created":"2023-09-27","cited_by_count":0,"area":null},{"id":"2407.05704","title":"Narrowing the Gap between Adversarial and Stochastic MDPs via Policy Optimization","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2409.18439","title":"State-free Reinforcement Learning","created":"2024-09-27","cited_by_count":0,"area":"deeprl"},{"id":"2505.13188","title":"When a Reinforcement Learning Agent Encounters Unknown Unknowns","created":"2025-05-19","cited_by_count":0,"area":"deeprl"},{"id":"2506.09940","title":"The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2509.03707","title":"Online Learning of Optimal Sequential Testing Policies","created":"2025-09-03","cited_by_count":0,"area":null},{"id":"2601.10418","title":"Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching","created":"2026-01-15","cited_by_count":0,"area":"deeprl"},{"id":"2603.01309","title":"PAC Guarantees for Reinforcement Learning: Sample Complexity, Coverage, and Structure","created":"2026-03-01","cited_by_count":0,"area":"deeprl"},{"id":"2603.03480","title":"Minimax Optimal Strategy for Delayed Observations in Online Reinforcement Learning","created":"2026-03-03","cited_by_count":0,"area":"deeprl"},{"id":"2603.06810","title":"Multi-Agent Reinforcement Learning with Submodular Reward","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2604.16684","title":"DARLING: Detection Augmented Reinforcement Learning with Non-Stationary Guarantees","created":"2026-04-17","cited_by_count":0,"area":"deeprl"},{"id":"2605.01242","title":"Breaking the Computational Barrier: Provably Efficient Actor-Critic for Low-Rank MDPs","created":"2026-05-02","cited_by_count":0,"area":"deeprl"},{"id":"2605.15692","title":"Tighter Regret Bounds for Contextual Action-Set Reinforcement Learning","created":"2026-05-15","cited_by_count":0,"area":"deeprl"},{"id":"2605.23182","title":"Pure Exploration for a Good Policy in Reinforcement Learning with Bandit Feedback","created":"2026-05-22","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}