{"total":57,"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":"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":"2105.01424","title":"On the Linear convergence of Natural Policy Gradient Algorithm","created":"2021-05-04","cited_by_count":48,"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":"2209.10579","title":"First-order Policy Optimization for Robust Markov Decision Process","created":"2022-09-21","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":"2210.00953","title":"Bias and Extrapolation in Markovian Linear Stochastic Approximation with Constant Stepsizes","created":"2022-10-03","cited_by_count":30,"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":"2102.09318","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm","created":"2021-02-18","cited_by_count":26,"area":null},{"id":"2108.03706","title":"Online Bootstrap Inference For Policy Evaluation in Reinforcement Learning","created":"2021-08-08","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":"2112.13109","title":"Accelerated and instance-optimal policy evaluation with linear function approximation","created":"2021-12-24","cited_by_count":18,"area":null},{"id":"2106.12729","title":"Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators","created":"2021-06-24","cited_by_count":17,"area":null},{"id":"2111.02997","title":"Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch","created":"2021-11-04","cited_by_count":17,"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":"2202.06828","title":"On the Convergence of SARSA with Linear Function Approximation","created":"2022-02-14","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":"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":"2411.13711","title":"Almost Sure Convergence Rates and Concentration of Stochastic Approximation and Reinforcement Learning with Markovian Noise","created":"2024-11-20","cited_by_count":12,"area":"deeprl"},{"id":"2501.19254","title":"Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set","created":"2025-01-31","cited_by_count":12,"area":"deeprl"},{"id":"2312.10424","title":"A Concentration Bound for TD(0) with Function Approximation","created":"2023-12-16","cited_by_count":10,"area":null},{"id":"2409.19546","title":"Asymptotic and Finite Sample Analysis of Nonexpansive Stochastic Approximations with Markovian Noise","created":"2024-09-29","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":"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":"2404.10635","title":"Compressed Federated Reinforcement Learning with a Generative Model","created":"2024-03-26","cited_by_count":6,"area":"deeprl"},{"id":"2505.21391","title":"Finite Sample Analysis of Linear Temporal Difference Learning with Arbitrary Features","created":"2025-05-27","cited_by_count":5,"area":"deeprl"},{"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":"2509.18964","title":"Central Limit Theorems for Asynchronous Averaged Q-Learning","created":"2025-09-23","cited_by_count":4,"area":null},{"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":"2202.02850","title":"Stochastic Gradient Descent with Dependent Data for Offline Reinforcement Learning","created":"2022-02-06","cited_by_count":2,"area":"offlinerl"},{"id":"2312.04905","title":"Two-Timescale Q-Learning with Function Approximation in Zero-Sum Stochastic Games","created":"2023-12-08","cited_by_count":2,"area":null},{"id":"2407.20128","title":"Finite-Sample Guarantees for Learning Dynamics in Zero-Sum Polymatrix Games","created":"2024-07-29","cited_by_count":2,"area":null},{"id":"2409.05733","title":"Markov Chain Variance Estimation: A Stochastic Approximation Approach","created":"2024-09-09","cited_by_count":2,"area":"deeprl"},{"id":"2503.17454","title":"Collaborative Value Function Estimation Under Model Mismatch: A Federated Temporal Difference Analysis","created":"2025-03-21","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":"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":"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":"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":"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":"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":"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":"2609.09480","title":"Gaussian Approximation in Wasserstein-p: Markovian Martingale Differences and Stochastic Approximation","created":"2026-09-08","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":"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":"2411.09731","title":"To bootstrap or to rollout? An optimal and adaptive interpolation","created":"2024-11-14","cited_by_count":0,"area":"deeprl"},{"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":"2608.01917","title":"Finite-Time Analysis of Discounted Exponential-Utility Reinforcement Learning","created":"2026-08-03","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}