{"total":57,"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":"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":"2102.08607","title":"On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method","created":"2021-02-17","cited_by_count":70,"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":"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":"2203.07368","title":"The Efficacy of Pessimism in Asynchronous Q-Learning","created":"2022-03-14","cited_by_count":42,"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":"2106.07046","title":"Towards Tight Bounds on the Sample Complexity of Average-reward MDPs","created":"2021-06-13","cited_by_count":33,"area":null},{"id":"2112.14582","title":"A Statistical Analysis of Polyak-Ruppert Averaged Q-learning","created":"2021-12-29","cited_by_count":29,"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":"2212.00603","title":"Near Sample-Optimal Reduction-based Policy Learning for Average Reward MDP","created":"2022-12-01","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":"2112.08451","title":"Quantum Algorithms for Reinforcement Learning with a Generative Model","created":"2021-12-15","cited_by_count":24,"area":null},{"id":"2106.14352","title":"Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning","created":"2021-06-28","cited_by_count":22,"area":null},{"id":"2305.19562","title":"Replicability in Reinforcement Learning","created":"2023-05-31","cited_by_count":21,"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":"2202.00308","title":"PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation","created":"2022-02-01","cited_by_count":17,"area":null},{"id":"2401.13884","title":"Constant Stepsize Q-learning: Distributional Convergence, Bias and Extrapolation","created":"2024-01-25","cited_by_count":17,"area":"deeprl"},{"id":"2208.10458","title":"Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model","created":"2022-08-22","cited_by_count":15,"area":null},{"id":"2108.05439","title":"Gap-Dependent Unsupervised Exploration for Reinforcement Learning","created":"2021-08-11","cited_by_count":10,"area":null},{"id":"2302.00727","title":"Sample Complexity of Kernel-Based Q-Learning","created":"2023-02-01","cited_by_count":8,"area":null},{"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":"2405.12952","title":"Truncated Variance Reduced Value Iteration","created":"2024-05-21","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":"2307.06877","title":"The complexity of non-stationary reinforcement learning","created":"2023-07-13","cited_by_count":7,"area":null},{"id":"2107.00685","title":"Gap-Dependent Bounds for Two-Player Markov Games","created":"2021-07-01","cited_by_count":5,"area":null},{"id":"2201.08536","title":"Instance-Dependent Confidence and Early Stopping for Reinforcement Learning","created":"2022-01-21","cited_by_count":5,"area":null},{"id":"2405.00282","title":"MF-OML: Online Mean-Field Reinforcement Learning with Occupation Measures for Large Population Games","created":"2024-05-01","cited_by_count":5,"area":"deeprl"},{"id":"2407.10454","title":"Deflated Dynamics Value Iteration","created":"2024-07-15","cited_by_count":5,"area":"deeprl"},{"id":"2506.00286","title":"Recursive Entropic Risk Optimization in Discounted MDPs: Sample Complexity Bounds with a Generative Model","created":"2025-05-30","cited_by_count":5,"area":"deeprl"},{"id":"2203.11489","title":"A Note on Target Q-learning For Solving Finite MDPs with A Generative Oracle","created":"2022-03-22","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":"2210.16872","title":"Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction","created":"2022-10-30","cited_by_count":4,"area":null},{"id":"2103.00299","title":"Primal-Dual Stochastic Mirror Descent for MDPs","created":"2021-02-27","cited_by_count":3,"area":null},{"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":"2606.16729","title":"Learning Policy from a Single Trajectory in Average-Reward Markov Decision Process","created":"2026-06-15","cited_by_count":3,"area":null},{"id":"2107.11053","title":"An Adaptive State Aggregation Algorithm for Markov Decision Processes","created":"2021-07-23","cited_by_count":2,"area":null},{"id":"2304.00232","title":"Restarted Bayesian Online Change-point Detection for Non-Stationary Markov Decision Processes","created":"2023-04-01","cited_by_count":2,"area":null},{"id":"2409.05908","title":"Faster Q-Learning Algorithms for Restless Bandits","created":"2024-09-06","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":"2510.17391","title":"Finite-Time Bounds for Average-Reward Fitted Q-Iteration","created":"2025-10-20","cited_by_count":2,"area":"offlinerl"},{"id":"2603.03759","title":"Learning Approximate Nash Equilibria in Cooperative Multi-Agent Reinforcement Learning via Mean-Field Subsampling","created":"2026-03-04","cited_by_count":2,"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":"2507.22854","title":"A Bit of Freedom Goes a Long Way: Classical and Quantum Algorithms for Reinforcement Learning under a Generative Model","created":"2025-07-30","cited_by_count":1,"area":"deeprl"},{"id":"2602.16196","title":"Graphon Mean-Field Subsampling for Cooperative Heterogeneous Multi-Agent Reinforcement Learning","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2604.06039","title":"Value Mirror Descent for Reinforcement Learning","created":"2026-04-07","cited_by_count":1,"area":"deeprl"},{"id":"2604.16111","title":"Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2605.21763","title":"On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents","created":"2026-05-20","cited_by_count":1,"area":"deeprl"},{"id":"2303.08856","title":"On the Benefits of Leveraging Structural Information in Planning Over the Learned Model","created":"2023-03-15","cited_by_count":0,"area":null},{"id":"2505.06769","title":"Value Iteration with Guessing for Markov Chains and Markov Decision Processes","created":"2025-05-10","cited_by_count":0,"area":null},{"id":"2510.09965","title":"Homomorphic Mappings for Value-Preserving State Aggregation in Markov Decision Processes","created":"2025-10-11","cited_by_count":0,"area":null},{"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"},{"id":"2608.02826","title":"Improved Quantum Algorithms for Reinforcement Learning Under a Generative Model","created":"2026-08-03","cited_by_count":0,"area":"deeprl"},{"id":"2610.06931","title":"Near-Optimal Sample Complexity for Recursive Entropic Risk Reinforcement Learning with a Generative Model","created":"2026-10-03","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}