{"total":81,"rows":[{"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":"2102.01567","title":"A Lyapunov Theory for Finite-Sample Guarantees of Asynchronous Q-Learning and TD-Learning Variants","created":"2021-02-02","cited_by_count":57,"area":null},{"id":"2102.01748","title":"Near-Optimal Offline Reinforcement Learning via Double Variance Reduction","created":"2021-02-02","cited_by_count":56,"area":"offlinerl"},{"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":"2102.04692","title":"Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap","created":"2021-02-09","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":"2101.12745","title":"Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP","created":"2021-01-29","cited_by_count":45,"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":"2108.02717","title":"Beyond No Regret: Instance-Dependent PAC Reinforcement Learning","created":"2021-08-05","cited_by_count":41,"area":null},{"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":"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":"2107.01264","title":"Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning","created":"2021-07-02","cited_by_count":34,"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":"2303.08059","title":"Fast Rates for Maximum Entropy Exploration","created":"2023-03-14","cited_by_count":33,"area":null},{"id":"2202.06385","title":"Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost","created":"2022-02-13","cited_by_count":32,"area":null},{"id":"2103.13056","title":"Minimax Regret for Stochastic Shortest Path","created":"2021-03-24","cited_by_count":30,"area":null},{"id":"2203.12922","title":"Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies","created":"2022-03-24","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":"2102.09318","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm","created":"2021-02-18","cited_by_count":26,"area":null},{"id":"2105.12540","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic with Linear Function Approximation","created":"2021-05-26","cited_by_count":22,"area":null},{"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":"2111.00633","title":"Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning","created":"2021-11-01","cited_by_count":18,"area":null},{"id":"2111.12679","title":"On the (In)Tractability of Reinforcement Learning for LTL Objectives","created":"2021-11-24","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":"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":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","cited_by_count":17,"area":null},{"id":"2107.08622","title":"Provably Efficient Multi-Task Reinforcement Learning with Model Transfer","created":"2021-07-19","cited_by_count":16,"area":null},{"id":"2212.04680","title":"Near-Optimal Differentially Private Reinforcement Learning","created":"2022-12-09","cited_by_count":16,"area":null},{"id":"2102.05214","title":"Task-Optimal Exploration in Linear Dynamical Systems","created":"2021-02-10","cited_by_count":15,"area":null},{"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":"2105.06029","title":"Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings","created":"2021-05-13","cited_by_count":14,"area":"offlinerl"},{"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":"2107.11927","title":"On Blame Attribution for Accountable Multi-Agent Sequential Decision Making","created":"2021-07-26","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":"2210.08238","title":"Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning","created":"2022-10-15","cited_by_count":13,"area":"offlinerl"},{"id":"2303.05518","title":"Computably Continuous Reinforcement-Learning Objectives are PAC-learnable","created":"2023-03-09","cited_by_count":13,"area":null},{"id":"2102.03400","title":"Confidence-Budget Matching for Sequential Budgeted Learning","created":"2021-02-05","cited_by_count":12,"area":null},{"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":"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":"2303.05606","title":"Variance-aware robust reinforcement learning with linear function approximation under heavy-tailed rewards","created":"2023-03-09","cited_by_count":8,"area":null},{"id":"2306.13601","title":"Active Coverage for PAC Reinforcement Learning","created":"2023-06-23","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":"2410.07574","title":"Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition","created":"2024-10-10","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":"2401.17780","title":"A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees","created":"2024-01-31","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":"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":"2406.02282","title":"Test-Time Regret Minimization in Meta Reinforcement Learning","created":"2024-06-04","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":"2210.04946","title":"Reaching Goals is Hard: Settling the Sample Complexity of the Stochastic Shortest Path","created":"2022-10-10","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":"2302.11634","title":"Provably Efficient Reinforcement Learning via Surprise Bound","created":"2023-02-22","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":"2402.01111","title":"Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints","created":"2024-02-02","cited_by_count":4,"area":"deeprl"},{"id":"2502.02859","title":"Gap-Dependent Bounds for Federated $Q$-learning","created":"2025-02-05","cited_by_count":4,"area":null},{"id":"2506.06521","title":"Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs","created":"2025-06-06","cited_by_count":4,"area":null},{"id":"2406.02165","title":"SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP","created":"2024-06-04","cited_by_count":3,"area":null},{"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":"2205.09056","title":"Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs","created":"2022-05-18","cited_by_count":2,"area":null},{"id":"2307.07666","title":"Efficient Action Robust Reinforcement Learning with Probabilistic Policy Execution Uncertainty","created":"2023-07-15","cited_by_count":2,"area":null},{"id":"2310.01616","title":"Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity","created":"2023-10-02","cited_by_count":2,"area":"offlinerl"},{"id":"2401.17880","title":"Graph Attention-based Reinforcement Learning for Trajectory Design and Resource Assignment in Multi-UAV Assisted Communication","created":"2024-01-31","cited_by_count":2,"area":"deeprl"},{"id":"2404.00195","title":"Multiple-policy Evaluation via Density Estimation","created":"2024-03-29","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":"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":"2105.02135","title":"UVIP: Model-Free Approach to Evaluate Reinforcement Learning Algorithms","created":"2021-05-05","cited_by_count":1,"area":null},{"id":"2510.06647","title":"Q-Learning with Fine-Grained Gap-Dependent Regret","created":"2025-10-08","cited_by_count":1,"area":"deeprl"},{"id":"2609.00193","title":"Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost","created":"2026-08-31","cited_by_count":1,"area":"deeprl"},{"id":"2210.13504","title":"Opportunistic Episodic Reinforcement Learning","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2211.12151","title":"Reinforcement Causal Structure Learning on Order Graph","created":"2022-11-22","cited_by_count":0,"area":null},{"id":"2305.02058","title":"Human Machine Co-adaption Interface via Cooperation Markov Decision Process System","created":"2023-05-03","cited_by_count":0,"area":null},{"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":"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":"2605.04979","title":"On-line Learning in Tree MDPs by Treating Policies as Bandit Arms","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2607.29294","title":"Sample Efficient Hierarchical Reinforcement Learning via Best Policy Identification","created":"2026-07-31","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}