{"total":96,"rows":[{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364,"area":"offlinerl"},{"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":"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":"2102.01567","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":"2102.01168","title":"Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges","created":"2021-01-27","cited_by_count":50,"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":"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":"2307.16212","title":"Robust Multi-Agent Reinforcement Learning with State Uncertainty","created":"2023-07-30","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":"2401.15273","title":"Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning","created":"2024-01-27","cited_by_count":31,"area":"deeprl"},{"id":"2112.14582","title":"A Statistical Analysis of Polyak-Ruppert Averaged Q-learning","created":"2021-12-29","cited_by_count":29,"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":"2303.15740","title":"Concentration of Contractive Stochastic Approximation: Additive and Multiplicative Noise","created":"2023-03-28","cited_by_count":26,"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":"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":"2208.11639","title":"Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path","created":"2022-08-24","cited_by_count":20,"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":"2206.09546","title":"Policy Optimization with Linear Temporal Logic Constraints","created":"2022-06-20","cited_by_count":19,"area":null},{"id":"2211.02147","title":"A Survey on Reinforcement Learning in Aviation Applications","created":"2022-11-03","cited_by_count":19,"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":"2401.13884","title":"Constant Stepsize Q-learning: Distributional Convergence, Bias and Extrapolation","created":"2024-01-25","cited_by_count":17,"area":"deeprl"},{"id":"2102.08583","title":"A Discrete-Time Switching System Analysis of Q-learning","created":"2021-02-17","cited_by_count":16,"area":null},{"id":"2403.02476","title":"A Simple Finite-Time Analysis of TD Learning with Linear Function Approximation","created":"2024-03-04","cited_by_count":16,"area":null},{"id":"2405.09999","title":"Reward Centering","created":"2024-05-16","cited_by_count":16,"area":"deeprl"},{"id":"2303.03100","title":"A Finite-Sample Analysis of Payoff-Based Independent Learning in Zero-Sum Stochastic Games","created":"2023-03-03","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":"2310.02147","title":"Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation","created":"2023-10-03","cited_by_count":14,"area":null},{"id":"2305.18443","title":"Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse","created":"2023-05-29","cited_by_count":12,"area":null},{"id":"2402.05876","title":"Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices","created":"2024-02-08","cited_by_count":11,"area":"offlinerl"},{"id":"2104.01627","title":"Finite-Time Convergence Rates of Nonlinear Two-Time-Scale Stochastic Approximation under Markovian Noise","created":"2021-04-04","cited_by_count":10,"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":"2303.04865","title":"Convergence Rates for Localized Actor-Critic in Networked Markov Potential Games","created":"2023-03-08","cited_by_count":9,"area":null},{"id":"2405.14285","title":"Computing the Bias of Constant-step Stochastic Approximation with Markovian Noise","created":"2024-05-23","cited_by_count":9,"area":null},{"id":"2408.16981","title":"The Sample-Communication Complexity Trade-off in Federated Q-Learning","created":"2024-08-30","cited_by_count":9,"area":"deeprl"},{"id":"2503.18391","title":"Finite-Time Bounds for Two-Time-Scale Stochastic Approximation with Arbitrary Norm Contractions and Markovian Noise","created":"2025-03-24","cited_by_count":9,"area":"deeprl"},{"id":"2302.12717","title":"Statistical Inference with Stochastic Gradient Methods under $\\phi$-mixing Data","created":"2023-02-24","cited_by_count":7,"area":null},{"id":"2308.01481","title":"Online covariance estimation for stochastic gradient descent under Markovian sampling","created":"2023-08-03","cited_by_count":7,"area":null},{"id":"2402.11800","title":"Stochastic Approximation with Delayed Updates: Finite-Time Rates under Markovian Sampling","created":"2024-02-19","cited_by_count":7,"area":"deeprl"},{"id":"2511.03618","title":"Towards Formalizing Reinforcement Learning Theory: A Robbins-Siegmund Approach","created":"2025-11-05","cited_by_count":7,"area":"deeprl"},{"id":"2206.11346","title":"Constrained Stochastic Nonconvex Optimization with State-dependent Markov Data","created":"2022-06-22","cited_by_count":6,"area":null},{"id":"2404.10635","title":"Compressed Federated Reinforcement Learning with a Generative Model","created":"2024-03-26","cited_by_count":6,"area":"deeprl"},{"id":"2112.04213","title":"Convergence Results For Q-Learning With Experience Replay","created":"2021-12-08","cited_by_count":5,"area":null},{"id":"2204.00006","title":"Data Sampling Affects the Complexity of Online SGD over Dependent Data","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2509.26442","title":"Extensions of Robbins-Siegmund Theorem with Applications in Reinforcement Learning","created":"2025-09-30","cited_by_count":5,"area":"deeprl"},{"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":"2207.12217","title":"Finite-Time Analysis of Asynchronous Q-learning under Diminishing Step-Size from Control-Theoretic View","created":"2022-07-25","cited_by_count":4,"area":null},{"id":"2505.21796","title":"A General-Purpose Theorem for High-Probability Bounds of Stochastic Approximation with Polyak Averaging","created":"2025-05-27","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":"2510.16132","title":"A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies","created":"2025-10-17","cited_by_count":4,"area":"deeprl"},{"id":"2208.03247","title":"An Approximate Policy Iteration Viewpoint of Actor-Critic Algorithms","created":"2022-08-05","cited_by_count":3,"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":"2403.06366","title":"Finite-Time Error Analysis of Soft Q-Learning: Switching System Approach","created":"2024-03-11","cited_by_count":3,"area":"deeprl"},{"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":"2202.02850","title":"Stochastic Gradient Descent with Dependent Data for Offline Reinforcement Learning","created":"2022-02-06","cited_by_count":2,"area":"offlinerl"},{"id":"2405.03718","title":"A Single Online Agent Can Efficiently Learn Mean Field Games","created":"2024-05-05","cited_by_count":2,"area":null},{"id":"2405.16053","title":"Pausing Policy Learning in Non-stationary Reinforcement Learning","created":"2024-05-25","cited_by_count":2,"area":"deeprl"},{"id":"2409.03237","title":"Robust Q-Learning under Corrupted Rewards","created":"2024-09-05","cited_by_count":2,"area":"deeprl"},{"id":"2504.11645","title":"Achieving Tighter Finite-Time Rates for Heterogeneous Federated Stochastic Approximation under Markovian Sampling","created":"2025-04-15","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":"2605.11021","title":"A Switching System Theory of Q-Learning with Linear Function Approximation","created":"2026-05-10","cited_by_count":2,"area":"deeprl"},{"id":"2111.12665","title":"Finite-Time Error Bounds for Distributed Linear Stochastic Approximation","created":"2021-11-24","cited_by_count":1,"area":null},{"id":"2310.06286","title":"Suppressing Overestimation in Q-Learning through Adversarial Behaviors","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2405.14078","title":"A finite time analysis of distributed Q-learning","created":"2024-05-23","cited_by_count":1,"area":"deeprl"},{"id":"2405.17463","title":"Is Thompson Sampling Susceptible to Algorithmic Collusion?","created":"2024-05-23","cited_by_count":1,"area":null},{"id":"2509.08933","title":"Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates","created":"2025-09-10","cited_by_count":1,"area":"deeprl"},{"id":"2510.07436","title":"Parameter-Free Federated TD Learning with Markov Noise in Heterogeneous Environments","created":"2025-10-08","cited_by_count":1,"area":"deeprl"},{"id":"2602.16274","title":"Regret and Sample Complexity of Online Q-Learning via Concentration of Stochastic Approximation with Time-Inhomogeneous Markov Chains","created":"2026-02-18","cited_by_count":1,"area":"deeprl"},{"id":"2604.07323","title":"Gaussian Approximation for Asynchronous Q-learning","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2605.07104","title":"Almost Sure Convergence Rates of Stochastic Approximation and Reinforcement Learning via a Poisson-Moreau Drift","created":"2026-05-08","cited_by_count":1,"area":"deeprl"},{"id":"2605.11289","title":"Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning","created":"2026-05-11","cited_by_count":1,"area":"deeprl"},{"id":"2605.16103","title":"Sign-Separated Asymmetric Finite-Time Error Analysis of Q-Learning","created":"2026-05-15","cited_by_count":1,"area":"deeprl"},{"id":"2605.31309","title":"Non-Asymptotic Convergence of Stochastic Iterative Algorithms: A Lyapunov Framework","created":"2026-05-29","cited_by_count":1,"area":"deeprl"},{"id":"2608.15966","title":"A Banach-Space Theory of Markovian Halpern Iteration for Non-Expansive Maps","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2609.20174","title":"Robust Federated Q-Learning with Almost No Communication","created":"2026-08-24","cited_by_count":1,"area":"deeprl"},{"id":"2609.38880","title":"Near-Minimax-Optimal Rates for Asynchronous TD Learning with Markovian Data","created":"2026-09-30","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":"2402.11877","title":"Learning the Model While Learning Q: Finite-Time Sample Complexity of Online SyncMBQ","created":"2024-02-19","cited_by_count":0,"area":"deeprl"},{"id":"2405.02201","title":"Regularized Q-learning through Robust Averaging","created":"2024-05-03","cited_by_count":0,"area":"deeprl"},{"id":"2408.06544","title":"Variance-Reduced Cascade Q-learning: Algorithms and Sample Complexity","created":"2024-08-13","cited_by_count":0,"area":"deeprl"},{"id":"2503.13414","title":"Provably Efficient Reward Transfer in Reinforcement Learning with Discrete Markov Decision Processes","created":"2025-03-17","cited_by_count":0,"area":"deeprl"},{"id":"2503.14927","title":"Semi-Gradient SARSA Routing with Theoretical Guarantee on Traffic Stability and Weight Convergence","created":"2025-03-19","cited_by_count":0,"area":null},{"id":"2511.16226","title":"Deep SOR Minimax Q-learning for Two-player Zero-sum Game","created":"2025-11-20","cited_by_count":0,"area":"deeprl"},{"id":"2602.05304","title":"A Short and Unified Convergence Analysis of the SAG, SAGA, and IAG Algorithms","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2604.04218","title":"Sharp asymptotic theory for Q-learning with LDTZ learning rate and its generalization","created":"2026-04-05","cited_by_count":0,"area":"deeprl"},{"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},{"id":"2606.20356","title":"Robust $Q$-learning for mean-field control under Wasserstein uncertainty in common noise","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.17595","title":"Concentration and Mean-Square Bounds for Contractive Stochastic Approximation: A Unified Elementary Approach","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.20822","title":"Robust Asynchronous Q-Learning under Reward and State Corruption via Batching","created":"2026-07-23","cited_by_count":0,"area":"deeprl"},{"id":"2607.21876","title":"Variance-Reduced Q-Learning over Static and Time-Varying Networks","created":"2026-07-24","cited_by_count":0,"area":"deeprl"},{"id":"2610.06918","title":"Learning from Unreliable Trajectories: Adversarially-Robust Federated Q-Learning","created":"2026-10-02","cited_by_count":0,"area":"deeprl"},{"id":"2610.13901","title":"Hitting-Time Bounds for Asynchronous Q-Learning","created":"2026-10-09","cited_by_count":0,"area":"deeprl"},{"id":"2610.18839","title":"Fast Rates for Offline Q-Learning with KL Regularization","created":"2026-10-13","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}