{"total":95,"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":"2208.05767","title":"Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity","created":"2022-08-11","cited_by_count":87,"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":"2204.05275","title":"Settling the Sample Complexity of Model-Based Offline Reinforcement Learning","created":"2022-04-11","cited_by_count":83,"area":"offlinerl"},{"id":"2105.15186","title":"Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization","created":"2021-05-31","cited_by_count":63,"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":"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":"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":"2210.01400","title":"Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies","created":"2022-10-04","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":"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":"2106.00198","title":"Gradient play in stochastic games: stationary points, convergence, and sample complexity","created":"2021-06-01","cited_by_count":34,"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":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","cited_by_count":31,"area":null},{"id":"2106.02847","title":"Navigating to the Best Policy in Markov Decision Processes","created":"2021-06-05","cited_by_count":29,"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":"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":"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":"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":"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":"2310.16173","title":"On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\\epsilon$-Greedy Exploration","created":"2023-10-24","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":"2305.19001","title":"High-probability sample complexities for policy evaluation with linear function approximation","created":"2023-05-30","cited_by_count":16,"area":null},{"id":"2302.06834","title":"Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization","created":"2023-02-14","cited_by_count":15,"area":null},{"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":"2305.17568","title":"Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities","created":"2023-05-27","cited_by_count":15,"area":null},{"id":"2210.00750","title":"Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient","created":"2022-10-03","cited_by_count":12,"area":"offlinerl"},{"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":"2302.01248","title":"Robust Markov Decision Processes without Model Estimation","created":"2023-02-02","cited_by_count":11,"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":"2202.13163","title":"Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons","created":"2022-02-26","cited_by_count":10,"area":"offlinerl"},{"id":"2312.10424","title":"A Concentration Bound for TD(0) with Function Approximation","created":"2023-12-16","cited_by_count":10,"area":null},{"id":"2406.17096","title":"Model-Free Robust Reinforcement Learning with Sample Complexity Analysis","created":"2024-06-24","cited_by_count":9,"area":"deeprl"},{"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":"2412.00661","title":"Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning","created":"2024-12-01","cited_by_count":9,"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":"2403.00222","title":"Efficient Reinforcement Learning for Global Decision Making in the Presence of Local Agents at Scale","created":"2024-03-01","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":"2511.03618","title":"Towards Formalizing Reinforcement Learning Theory: A Robbins-Siegmund Approach","created":"2025-11-05","cited_by_count":7,"area":"deeprl"},{"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":"2201.08536","title":"Instance-Dependent Confidence and Early Stopping for Reinforcement Learning","created":"2022-01-21","cited_by_count":5,"area":null},{"id":"2207.06147","title":"A Near-Optimal Primal-Dual Method for Off-Policy Learning in CMDP","created":"2022-07-13","cited_by_count":5,"area":null},{"id":"2408.05686","title":"The Bandit Whisperer: Communication Learning for Restless Bandits","created":"2024-08-11","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":"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":"2211.07675","title":"On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network Parametrization","created":"2022-11-14","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":"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":"2110.02421","title":"Explaining Off-Policy Actor-Critic From A Bias-Variance Perspective","created":"2021-10-06","cited_by_count":2,"area":null},{"id":"2302.07938","title":"Scalable Multi-Agent Reinforcement Learning with General Utilities","created":"2023-02-15","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":"2405.03967","title":"SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems","created":"2024-05-07","cited_by_count":2,"area":"deeprl"},{"id":"2406.18351","title":"Reinforcement Learning with Intrinsically Motivated Feedback Graph for Lost-sales Inventory Control","created":"2024-06-26","cited_by_count":2,"area":"deeprl"},{"id":"2409.03897","title":"On the Convergence Rates of Federated Q-Learning across Heterogeneous Environments","created":"2024-09-05","cited_by_count":2,"area":"deeprl"},{"id":"2410.10737","title":"Asymptotic Analysis of Sample-averaged Q-learning","created":"2024-10-14","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":"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":"2606.24981","title":"A Single Stepsize Suffices for Unprojected Linear TD(0): Simultaneous Robust and Fast Rates via Polyak--Ruppert Averaging","created":"2026-06-23","cited_by_count":2,"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":"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":"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":"2605.16103","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":"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":"2111.02644","title":"A Concentration Bound for LSPE($\\lambda$)","created":"2021-11-04","cited_by_count":0,"area":null},{"id":"2204.10479","title":"Finite-Time Accuracy of Temporal-Difference Learning Under Schur-Stable Recursions","created":"2022-04-22","cited_by_count":0,"area":null},{"id":"2305.06657","title":"On Practical Robust Reinforcement Learning: Practical Uncertainty Set and Double-Agent Algorithm","created":"2023-05-11","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},{"id":"2406.09946","title":"Finite-Time Analysis of Simultaneous Double Q-learning","created":"2024-06-14","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":"2408.16999","title":"A Tighter Convergence Proof of Reverse Experience Replay","created":"2024-08-30","cited_by_count":0,"area":"deeprl"},{"id":"2512.17265","title":"A Theoretical Analysis of State Similarity Between Markov Decision Processes","created":"2025-12-19","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":"2604.04394","title":"Finite-Time Analysis of Q-Value Iteration for General-Sum Stackelberg Games","created":"2026-04-06","cited_by_count":0,"area":"deeprl"},{"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":"2607.06935","title":"Mathematical methods of reinforcement learning","created":"2026-07-08","cited_by_count":0,"area":"deeprl"},{"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":"2609.23775","title":"Statistical Convergence of Transformer Encoder-Accelerated Robust Reinforcement Learning","created":"2026-09-20","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}