{"total":48,"rows":[{"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":"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":"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":"2305.16589","title":"The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model","created":"2023-05-26","cited_by_count":52,"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":"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":"2305.18420","title":"Sample Complexity of Variance-reduced Distributionally Robust Q-learning","created":"2023-05-28","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":"2102.09318","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm","created":"2021-02-18","cited_by_count":26,"area":null},{"id":"2404.18909","title":"Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty","created":"2024-04-29","cited_by_count":25,"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":"2103.12158","title":"Convergence of Finite Memory Q-Learning for POMDPs and Near Optimality of Learned Policies under Filter Stability","created":"2021-03-22","cited_by_count":22,"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":"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":"2201.08518","title":"Optimal variance-reduced stochastic approximation in Banach spaces","created":"2022-01-21","cited_by_count":17,"area":null},{"id":"2102.08583","title":"A Discrete-Time Switching System Analysis of Q-learning","created":"2021-02-17","cited_by_count":16,"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":"2312.02828","title":"Convergence Rates for Stochastic Approximation: Biased Noise with Unbounded Variance, and Applications","created":"2023-12-05","cited_by_count":15,"area":null},{"id":"2401.00364","title":"Tight Finite Time Bounds of Two-Time-Scale Linear Stochastic Approximation with Markovian Noise","created":"2023-12-31","cited_by_count":15,"area":null},{"id":"2302.01248","title":"Robust Markov Decision Processes without Model Estimation","created":"2023-02-02","cited_by_count":11,"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":"2405.17834","title":"Revisiting Step-Size Assumptions in Stochastic Approximation","created":"2024-05-28","cited_by_count":10,"area":null},{"id":"2211.13937","title":"Operator Splitting Value Iteration","created":"2022-11-25","cited_by_count":8,"area":null},{"id":"2307.02632","title":"Stability of Q-Learning Through Design and Optimism","created":"2023-07-05","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":"2302.07477","title":"Optimal Sample Complexity of Stable Discounted Markov Decision Processes","created":"2023-02-15","cited_by_count":6,"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":"2112.07859","title":"Finite-Sample Analysis of Decentralized Q-Learning for Stochastic Games","created":"2021-12-15","cited_by_count":4,"area":null},{"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":"2509.18964","title":"Central Limit Theorems for Asynchronous Averaged Q-Learning","created":"2025-09-23","cited_by_count":4,"area":null},{"id":"2306.05700","title":"Finite-Time Analysis of Minimax Q-Learning for Two-Player Zero-Sum Markov Games: Switching System Approach","created":"2023-06-09","cited_by_count":3,"area":null},{"id":"2407.06712","title":"MDP Geometry, Normalization and Reward Balancing Solvers","created":"2024-07-09","cited_by_count":3,"area":null},{"id":"2505.01828","title":"Rank-One Modified Value Iteration","created":"2025-05-03","cited_by_count":3,"area":null},{"id":"2607.09097","title":"Solving Stochastic Fixed-Point Equations with High Probability","created":"2026-07-10","cited_by_count":3,"area":null},{"id":"2508.05984","title":"Parameter-free Optimal Rates for Nonlinear Semi-Norm Contractions with Applications to $Q$-Learning","created":"2025-08-08","cited_by_count":2,"area":null},{"id":"2510.12013","title":"Statistical Guarantees for High-Dimensional Stochastic Gradient Descent","created":"2025-10-13","cited_by_count":2,"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":"2604.07323","title":"Gaussian Approximation for Asynchronous Q-learning","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2109.03445","title":"Convergence of Batch Asynchronous Stochastic Approximation With Applications to Reinforcement Learning","created":"2021-09-08","cited_by_count":0,"area":null},{"id":"2111.02644","title":"A Concentration Bound for LSPE($\\lambda$)","created":"2021-11-04","cited_by_count":0,"area":null},{"id":"2401.06710","title":"Model-Free Approximate Bayesian Learning for Large-Scale Conversion Funnel Optimization","created":"2024-01-12","cited_by_count":0,"area":null}],"next_cursor":null}