{"total":50,"rows":[{"id":"2201.07443","title":"On the Convergence Rates of Policy Gradient Methods","created":"2022-01-19","cited_by_count":119,"area":null},{"id":"2109.14523","title":"Online Robust Reinforcement Learning with Model Uncertainty","created":"2021-09-29","cited_by_count":96,"area":null},{"id":"2102.06548","title":"Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis","created":"2021-02-12","cited_by_count":92,"area":null},{"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":"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":"2302.13203","title":"A Finite Sample Complexity Bound for Distributionally Robust Q-learning","created":"2023-02-26","cited_by_count":36,"area":null},{"id":"2305.10697","title":"The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond","created":"2023-05-18","cited_by_count":36,"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":"2205.05800","title":"Stochastic first-order methods for average-reward Markov decision processes","created":"2022-05-11","cited_by_count":32,"area":null},{"id":"2203.02628","title":"Target Network and Truncation Overcome The Deadly Triad in $Q$-Learning","created":"2022-03-05","cited_by_count":31,"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":"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":"2305.18420","title":"Sample Complexity of Variance-reduced Distributionally Robust Q-learning","created":"2023-05-28","cited_by_count":29,"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":"2106.14308","title":"Concentration of Contractive Stochastic Approximation and Reinforcement Learning","created":"2021-06-27","cited_by_count":23,"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":"2110.08440","title":"Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs","created":"2021-10-16","cited_by_count":19,"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":"2112.13109","title":"Accelerated and instance-optimal policy evaluation with linear function approximation","created":"2021-12-24","cited_by_count":18,"area":null},{"id":"2302.11381","title":"Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision Processes","created":"2023-02-22","cited_by_count":18,"area":null},{"id":"2201.08518","title":"Optimal variance-reduced stochastic approximation in Banach spaces","created":"2022-01-21","cited_by_count":17,"area":null},{"id":"2403.11477","title":"Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs","created":"2024-03-18","cited_by_count":17,"area":null},{"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":"2310.08833","title":"Optimal Sample Complexity for Average Reward Markov Decision Processes","created":"2023-10-13","cited_by_count":15,"area":null},{"id":"2205.14211","title":"KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal","created":"2022-05-27","cited_by_count":13,"area":null},{"id":"2312.10424","title":"A Concentration Bound for TD(0) with Function Approximation","created":"2023-12-16","cited_by_count":10,"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":"2103.16377","title":"Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved Complexity","created":"2021-03-30","cited_by_count":7,"area":null},{"id":"2302.07477","title":"Optimal Sample Complexity of Stable Discounted Markov Decision Processes","created":"2023-02-15","cited_by_count":6,"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":"2206.00796","title":"Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2311.13469","title":"Span-Based Optimal Sample Complexity for Average Reward MDPs","created":"2023-11-22","cited_by_count":5,"area":null},{"id":"2206.01666","title":"Algorithm for Constrained Markov Decision Process with Linear Convergence","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2107.08083","title":"Robust Risk-Sensitive Reinforcement Learning Agents for Trading Markets","created":"2021-07-16","cited_by_count":3,"area":null},{"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":"2502.15345","title":"Efficiently Solving Discounted MDPs with Predictions on Transition Matrices","created":"2025-02-21","cited_by_count":2,"area":null},{"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":"2105.02135","title":"UVIP: Model-Free Approach to Evaluate Reinforcement Learning Algorithms","created":"2021-05-05","cited_by_count":1,"area":null},{"id":"2404.00042","title":"Stochastic Optimization with Constraints: A Non-asymptotic Instance-Dependent Analysis","created":"2024-03-24","cited_by_count":1,"area":null},{"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":"2604.07323","title":"Gaussian Approximation for Asynchronous Q-learning","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2606.25170","title":"Minimax PAC Bounds for Learning in Exogenous Contextual MDPs","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2111.02644","title":"A Concentration Bound for LSPE($\\lambda$)","created":"2021-11-04","cited_by_count":0,"area":null},{"id":"2302.10434","title":"Kernel-Based Distributed Q-Learning: A Scalable Reinforcement Learning Approach for Dynamic Treatment Regimes","created":"2023-02-21","cited_by_count":0,"area":null},{"id":"2310.17915","title":"Lifting the Veil: Unlocking the Power of Depth in Q-learning","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2405.04026","title":"Federated Control in Markov Decision Processes","created":"2024-05-07","cited_by_count":0,"area":null},{"id":"2510.22744","title":"OEUVRE: OnlinE Unbiased Variance-Reduced loss Estimation","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2605.17678","title":"On Gaussian approximation for entropy-regularized Q-learning with function approximation","created":"2026-05-17","cited_by_count":0,"area":null}],"next_cursor":null}