{"total":101,"rows":[{"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":"2110.00871","title":"Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning","created":"2021-10-02","cited_by_count":66,"area":null},{"id":"2210.09579","title":"Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity","created":"2022-10-18","cited_by_count":62,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2212.06132","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes","created":"2022-12-12","cited_by_count":57,"area":null},{"id":"2103.12923","title":"Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation","created":"2021-03-24","cited_by_count":53,"area":null},{"id":"2107.08346","title":"Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses","created":"2021-07-18","cited_by_count":52,"area":null},{"id":"2205.11507","title":"Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs","created":"2022-05-23","cited_by_count":52,"area":null},{"id":"2106.07841","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","created":"2021-06-15","cited_by_count":49,"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":"2211.04974","title":"Leveraging Offline Data in Online Reinforcement Learning","created":"2022-11-09","cited_by_count":42,"area":"offlinerl"},{"id":"2101.00494","title":"A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost","created":"2021-01-02","cited_by_count":40,"area":null},{"id":"2302.10371","title":"Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency","created":"2023-02-21","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":"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":"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":"2102.05800","title":"Robust Policy Gradient against Strong Data Corruption","created":"2021-02-11","cited_by_count":30,"area":null},{"id":"2103.13056","title":"Minimax Regret for Stochastic Shortest Path","created":"2021-03-24","cited_by_count":30,"area":null},{"id":"2206.11489","title":"Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation","created":"2022-06-23","cited_by_count":30,"area":null},{"id":"2110.06394","title":"Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation","created":"2021-10-12","cited_by_count":29,"area":null},{"id":"2305.18246","title":"Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo","created":"2023-05-29","cited_by_count":29,"area":null},{"id":"2102.08940","title":"Near-optimal Policy Optimization Algorithms for Learning Adversarial Linear Mixture MDPs","created":"2021-02-17","cited_by_count":28,"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":"2105.06022","title":"Principled Exploration via Optimistic Bootstrapping and Backward Induction","created":"2021-05-13","cited_by_count":26,"area":null},{"id":"2102.07404","title":"Almost Optimal Algorithms for Two-player Zero-Sum Linear Mixture Markov Games","created":"2021-02-15","cited_by_count":25,"area":null},{"id":"2402.15399","title":"Distributionally Robust Off-Dynamics Reinforcement Learning: Provable Efficiency with Linear Function Approximation","created":"2024-02-23","cited_by_count":25,"area":"deeprl"},{"id":"2011.04019","title":"Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient","created":"2020-11-08","cited_by_count":24,"area":"offlinerl"},{"id":"2206.04640","title":"Regret Bounds for Information-Directed Reinforcement Learning","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2110.12727","title":"Learning Stochastic Shortest Path with Linear Function Approximation","created":"2021-10-25","cited_by_count":23,"area":null},{"id":"2201.13172","title":"Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback","created":"2022-01-31","cited_by_count":22,"area":null},{"id":"2110.09771","title":"On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game","created":"2021-10-19","cited_by_count":20,"area":null},{"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":"2306.07745","title":"Kernelized Reinforcement Learning with Order Optimal Regret Bounds","created":"2023-06-13","cited_by_count":20,"area":null},{"id":"2105.14016","title":"Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model","created":"2021-05-28","cited_by_count":18,"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":"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":"2501.17827","title":"Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning","created":"2025-01-29","cited_by_count":17,"area":"deeprl"},{"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":"2409.20521","title":"Upper and Lower Bounds for Distributionally Robust Off-Dynamics Reinforcement Learning","created":"2024-09-30","cited_by_count":16,"area":"deeprl"},{"id":"2102.09703","title":"Near-Optimal Randomized Exploration for Tabular Markov Decision Processes","created":"2021-02-19","cited_by_count":15,"area":null},{"id":"2105.01593","title":"Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation","created":"2021-05-04","cited_by_count":15,"area":null},{"id":"2302.06834","title":"Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization","created":"2023-02-14","cited_by_count":15,"area":null},{"id":"2112.09859","title":"Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDP","created":"2021-12-18","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":"2104.07794","title":"An $L^2$ Analysis of Reinforcement Learning in High Dimensions with Kernel and Neural Network Approximation","created":"2021-04-15","cited_by_count":13,"area":null},{"id":"2212.13540","title":"Model-Based Reinforcement Learning with Multinomial Logistic Function Approximation","created":"2022-12-27","cited_by_count":13,"area":null},{"id":"2209.14414","title":"Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees","created":"2022-09-28","cited_by_count":12,"area":null},{"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":"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":"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":"2310.01380","title":"Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning","created":"2023-10-02","cited_by_count":9,"area":"offlinerl"},{"id":"2303.10165","title":"Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs","created":"2023-03-17","cited_by_count":7,"area":null},{"id":"2310.20007","title":"Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2311.08376","title":"Ensemble sampling for linear bandits: small ensembles suffice","created":"2023-11-14","cited_by_count":7,"area":null},{"id":"2509.08660","title":"Replicable Reinforcement Learning with Linear Function Approximation","created":"2025-09-10","cited_by_count":7,"area":"deeprl"},{"id":"2109.05546","title":"Improved Algorithms for Misspecified Linear Markov Decision Processes","created":"2021-09-12","cited_by_count":6,"area":null},{"id":"2305.07911","title":"Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedback","created":"2023-05-13","cited_by_count":6,"area":null},{"id":"2407.13755","title":"Random Latent Exploration for Deep Reinforcement Learning","created":"2024-07-18","cited_by_count":6,"area":"deeprl"},{"id":"2502.10138","title":"Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation","created":"2025-02-14","cited_by_count":6,"area":"deeprl"},{"id":"2112.14195","title":"Exponential Family Model-Based Reinforcement Learning via Score Matching","created":"2021-12-28","cited_by_count":5,"area":null},{"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":"2406.11810","title":"Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics","created":"2024-06-17","cited_by_count":5,"area":"deeprl"},{"id":"2407.03065","title":"Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes","created":"2024-07-03","cited_by_count":5,"area":"deeprl"},{"id":"2201.13170","title":"Cooperative Online Learning in Stochastic and Adversarial MDPs","created":"2022-01-31","cited_by_count":4,"area":null},{"id":"2204.10349","title":"Provably Efficient Kernelized Q-Learning","created":"2022-04-21","cited_by_count":4,"area":null},{"id":"2301.12038","title":"STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning","created":"2023-01-28","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":"2410.24089","title":"Demystifying Linear MDPs and Novel Dynamics Aggregation Framework","created":"2024-10-31","cited_by_count":4,"area":null},{"id":"2310.15286","title":"A Doubly Robust Approach to Sparse Reinforcement Learning","created":"2023-10-23","cited_by_count":3,"area":null},{"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":"2404.10745","title":"Achieving Constant Regret in Linear Markov Decision Processes","created":"2024-04-16","cited_by_count":3,"area":"deeprl"},{"id":"2506.09508","title":"Efficient Preference-Based Reinforcement Learning: Randomized Exploration Meets Experimental Design","created":"2025-06-11","cited_by_count":3,"area":"alignment"},{"id":"2403.11175","title":"Prior-dependent analysis of posterior sampling reinforcement learning with function approximation","created":"2024-03-17","cited_by_count":2,"area":"deeprl"},{"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":"2503.00810","title":"Minimax Optimal Reinforcement Learning with Quasi-Optimism","created":"2025-03-02","cited_by_count":2,"area":"deeprl"},{"id":"2506.24005","title":"Provably Efficient and Agile Randomized Q-Learning","created":"2025-06-30","cited_by_count":2,"area":"deeprl"},{"id":"2602.06014","title":"Optimism Stabilizes Thompson Sampling for Adaptive Inference","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2107.05849","title":"Model Selection for Generic Reinforcement Learning","created":"2021-07-13","cited_by_count":1,"area":null},{"id":"2207.02992","title":"Model Selection in Reinforcement Learning with General Function Approximations","created":"2022-07-06","cited_by_count":1,"area":null},{"id":"2308.07843","title":"Dyadic Reinforcement Learning","created":"2023-08-15","cited_by_count":1,"area":null},{"id":"2402.08998","title":"Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path","created":"2024-02-14","cited_by_count":1,"area":null},{"id":"2410.14992","title":"Learning Infinite-Horizon Average-Reward Linear Mixture MDPs of Bounded Span","created":"2024-10-19","cited_by_count":1,"area":null},{"id":"2502.07715","title":"Near-Optimal Sample Complexity in Reward-Free Kernel-Based Reinforcement Learning","created":"2025-02-11","cited_by_count":1,"area":"deeprl"},{"id":"2503.18980","title":"CAE: Repurposing the Critic as an Explorer in Deep Reinforcement Learning","created":"2025-03-23","cited_by_count":1,"area":"deeprl"},{"id":"2506.00917","title":"Q-learning with Posterior Sampling","created":"2025-06-01","cited_by_count":1,"area":"deeprl"},{"id":"2511.07831","title":"Distributionally Robust Online Markov Game with Linear Function Approximation","created":"2025-11-11","cited_by_count":1,"area":"deeprl"},{"id":"2301.03142","title":"Exploration in Model-based Reinforcement Learning with Randomized Reward","created":"2023-01-09","cited_by_count":0,"area":null},{"id":"2501.13394","title":"Concurrent Learning with Aggregated States via Randomized Least Squares Value Iteration","created":"2025-01-23","cited_by_count":0,"area":"deeprl"},{"id":"2505.23927","title":"Thompson Sampling in Online RLHF with General Function Approximation","created":"2025-05-29","cited_by_count":0,"area":"alignment"},{"id":"2510.17390","title":"Exploration via Feature Perturbation in Contextual Bandits","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2511.03473","title":"Reinforcement Learning Using known Invariances","created":"2025-11-05","cited_by_count":0,"area":"deeprl"},{"id":"2602.10838","title":"Mirror descent actor-critic methods for entropy regularised MDPs in general spaces: stability and convergence","created":"2026-02-11","cited_by_count":0,"area":"deeprl"},{"id":"2603.09208","title":"Strategically Robust Multi-Agent Reinforcement Learning with Linear Function Approximation","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.23461","title":"End-to-End Efficient RL for Linear Bellman Complete MDPs with Deterministic Transitions","created":"2026-03-24","cited_by_count":0,"area":"deeprl"},{"id":"2605.23650","title":"Learning Kernel-Based MDPs from Episodic Preferential Feedback","created":"2026-05-22","cited_by_count":0,"area":"alignment"},{"id":"2605.24939","title":"Global linear convergence of entropy-regularized softmax policy gradient beyond tabular MDPs","created":"2026-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2606.01952","title":"Randomized Least Squares Value Iteration itself is Joint Differentially Private","created":"2026-06-01","cited_by_count":0,"area":"deeprl"},{"id":"2606.28616","title":"Randomized Exploration for Linear Bandits via Absolute Perturbations","created":"2026-06-26","cited_by_count":0,"area":null}],"next_cursor":"100"}