{"total":159,"rows":[{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"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":"2205.07344","title":"Policy Gradient Method For Robust Reinforcement Learning","created":"2022-05-15","cited_by_count":69,"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":"2105.01424","title":"On the Linear convergence of Natural Policy Gradient Algorithm","created":"2021-05-04","cited_by_count":48,"area":null},{"id":"2207.04475","title":"Finite-time High-probability Bounds for Polyak-Ruppert Averaged Iterates of Linear Stochastic Approximation","created":"2022-07-10","cited_by_count":41,"area":null},{"id":"2101.10506","title":"Finite Sample Analysis of Two-Time-Scale Natural Actor-Critic Algorithm","created":"2021-01-26","cited_by_count":39,"area":null},{"id":"2105.04646","title":"Deeply-Debiased Off-Policy Interval Estimation","created":"2021-05-10","cited_by_count":36,"area":null},{"id":"2202.04428","title":"Adapting to Mixing Time in Stochastic Optimization with Markovian Data","created":"2022-02-09","cited_by_count":36,"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":"2210.09921","title":"Finite-time analysis of single-timescale actor-critic","created":"2022-10-18","cited_by_count":32,"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":"2108.02731","title":"Mean-Field Multi-Agent Reinforcement Learning: A Decentralized Network Approach","created":"2021-08-05","cited_by_count":28,"area":null},{"id":"2106.01257","title":"Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize","created":"2021-06-02","cited_by_count":27,"area":null},{"id":"2302.02212","title":"Federated Temporal Difference Learning with Linear Function Approximation under Environmental Heterogeneity","created":"2023-02-04","cited_by_count":27,"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":"2109.03699","title":"Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysis","created":"2021-09-08","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":"2203.02591","title":"A Small Gain Analysis of Single Timescale Actor Critic","created":"2022-03-04","cited_by_count":24,"area":null},{"id":"2102.00185","title":"On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning","created":"2021-01-30","cited_by_count":23,"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":"2210.05918","title":"Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation","created":"2022-10-12","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":"2106.13781","title":"Tighter Analysis of Alternating Stochastic Gradient Method for Stochastic Nested Problems","created":"2021-06-25","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":"2206.00833","title":"Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm","created":"2022-06-02","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":"2312.11669","title":"Prediction and Control in Continual Reinforcement Learning","created":"2023-12-18","cited_by_count":19,"area":null},{"id":"2405.16644","title":"Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learning","created":"2024-05-26","cited_by_count":19,"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":"2301.12083","title":"Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic","created":"2023-01-28","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":"2202.06915","title":"Stochastic linear optimization never overfits with quadratically-bounded losses on general data","created":"2022-02-14","cited_by_count":17,"area":null},{"id":"2206.10414","title":"A Single-Timescale Analysis For Stochastic Approximation With Multiple Coupled Sequences","created":"2022-06-21","cited_by_count":17,"area":null},{"id":"2209.15382","title":"Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization","created":"2022-09-30","cited_by_count":17,"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":"2401.15719","title":"Rates of Convergence in the Central Limit Theorem for Markov Chains, with an Application to TD Learning","created":"2024-01-28","cited_by_count":17,"area":null},{"id":"2106.04096","title":"Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation","created":"2021-06-08","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":"2306.17750","title":"TD Convergence: An Optimization Perspective","created":"2023-06-30","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":"2305.08104","title":"Federated TD Learning over Finite-Rate Erasure Channels: Linear Speedup under Markovian Sampling","created":"2023-05-14","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":"2106.07472","title":"Analysis of a Target-Based Actor-Critic Algorithm with Linear Function Approximation","created":"2021-06-14","cited_by_count":14,"area":null},{"id":"2305.15938","title":"First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities","created":"2023-05-25","cited_by_count":14,"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":"2110.11280","title":"Actor-critic is implicitly biased towards high entropy optimal policies","created":"2021-10-21","cited_by_count":13,"area":null},{"id":"2111.06328","title":"Stationary Behavior of Constant Stepsize SGD Type Algorithms: An Asymptotic Characterization","created":"2021-11-11","cited_by_count":13,"area":null},{"id":"2202.09753","title":"Finite-Time Analysis of Natural Actor-Critic for POMDPs","created":"2022-02-20","cited_by_count":13,"area":null},{"id":"2302.12537","title":"Why Target Networks Stabilise Temporal Difference Methods","created":"2023-02-24","cited_by_count":13,"area":null},{"id":"2303.04386","title":"Policy Mirror Descent Inherently Explores Action Space","created":"2023-03-08","cited_by_count":13,"area":null},{"id":"2305.16246","title":"Distributed TD(0) with Almost No Communication","created":"2023-05-25","cited_by_count":13,"area":null},{"id":"2301.00944","title":"Temporal Difference Learning with Compressed Updates: Error-Feedback meets Reinforcement Learning","created":"2023-01-03","cited_by_count":12,"area":null},{"id":"2103.01391","title":"Sample Complexity and Overparameterization Bounds for Temporal Difference Learning with Neural Network Approximation","created":"2021-03-02","cited_by_count":10,"area":null},{"id":"2108.05338","title":"Truncated Emphatic Temporal Difference Methods for Prediction and Control","created":"2021-08-11","cited_by_count":10,"area":null},{"id":"2302.11147","title":"Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning","created":"2023-02-22","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":"2405.17834","title":"Revisiting Step-Size Assumptions in Stochastic Approximation","created":"2024-05-28","cited_by_count":10,"area":null},{"id":"2301.09709","title":"On The Convergence Of Policy Iteration-Based Reinforcement Learning With Monte Carlo Policy Evaluation","created":"2023-01-23","cited_by_count":9,"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":"2305.02456","title":"Streaming PCA for Markovian Data","created":"2023-05-03","cited_by_count":9,"area":null},{"id":"2306.11455","title":"Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards","created":"2023-06-20","cited_by_count":9,"area":null},{"id":"2104.02836","title":"Non-Asymptotic Analysis for Two Time-scale TDC with General Smooth Function Approximation","created":"2021-04-07","cited_by_count":8,"area":null},{"id":"2208.08744","title":"Global Convergence of Two-timescale Actor-Critic for Solving Linear Quadratic Regulator","created":"2022-08-18","cited_by_count":8,"area":null},{"id":"2301.13289","title":"On the Statistical Benefits of Temporal Difference Learning","created":"2023-01-30","cited_by_count":8,"area":null},{"id":"2201.10447","title":"Differentially Private Temporal Difference Learning with Stochastic Nonconvex-Strongly-Concave Optimization","created":"2022-01-25","cited_by_count":7,"area":null},{"id":"2203.04236","title":"A Complete Characterization of Linear Estimators for Offline Policy Evaluation","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2203.15797","title":"Convergence of First-Order Methods for Constrained Nonconvex Optimization with Dependent Data","created":"2022-03-29","cited_by_count":7,"area":null},{"id":"2301.02220","title":"Value Enhancement of Reinforcement Learning via Efficient and Robust Trust Region Optimization","created":"2023-01-05","cited_by_count":7,"area":null},{"id":"2308.01170","title":"Revisiting a Design Choice in Gradient Temporal Difference Learning","created":"2023-08-02","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":"2401.12764","title":"Fast Nonlinear Two-Time-Scale Stochastic Approximation: Achieving $O(1/k)$ Finite-Sample Complexity","created":"2024-01-23","cited_by_count":7,"area":null},{"id":"2402.04114","title":"SCAFFLSA: Taming Heterogeneity in Federated Linear Stochastic Approximation and TD Learning","created":"2024-02-06","cited_by_count":7,"area":null},{"id":"2407.05966","title":"On Bellman equations for continuous-time policy evaluation I: discretization and approximation","created":"2024-07-08","cited_by_count":7,"area":null},{"id":"2110.05597","title":"Learning to Coordinate in Multi-Agent Systems: A Coordinated Actor-Critic Algorithm and Finite-Time Guarantees","created":"2021-10-11","cited_by_count":6,"area":null},{"id":"2206.11346","title":"Constrained Stochastic Nonconvex Optimization with State-dependent Markov Data","created":"2022-06-22","cited_by_count":6,"area":null},{"id":"2312.05397","title":"On the Performance of Temporal Difference Learning With Neural Networks","created":"2023-12-08","cited_by_count":6,"area":null},{"id":"2502.14172","title":"A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximation","created":"2025-02-20","cited_by_count":6,"area":null},{"id":"2103.13147","title":"Multi-Agent Off-Policy TD Learning: Finite-Time Analysis with Near-Optimal Sample Complexity and Communication Complexity","created":"2021-03-24","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":"2312.10894","title":"Effectiveness of Constant Stepsize in Markovian LSA and Statistical Inference","created":"2023-12-18","cited_by_count":5,"area":null},{"id":"2402.02857","title":"Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2408.08192","title":"Stochastic Semi-Gradient Descent for Learning Mean Field Games with Population-Aware Function Approximation","created":"2024-08-15","cited_by_count":5,"area":null},{"id":"2410.13067","title":"Two-Timescale Linear Stochastic Approximation: Constant Stepsizes Go a Long Way","created":"2024-10-16","cited_by_count":5,"area":null},{"id":"2112.00882","title":"Robust and Adaptive Temporal-Difference Learning Using An Ensemble of Gaussian Processes","created":"2021-12-01","cited_by_count":4,"area":null},{"id":"2202.10574","title":"A Multi-Agent Reinforcement Learning Framework for Off-Policy Evaluation in Two-sided Markets","created":"2022-02-21","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":"2305.07248","title":"Quantile-Based Deep Reinforcement Learning using Two-Timescale Policy Gradient Algorithms","created":"2023-05-12","cited_by_count":4,"area":null},{"id":"2403.15935","title":"Sample and Communication Efficient Fully Decentralized MARL Policy Evaluation via a New Approach: Local TD update","created":"2024-03-23","cited_by_count":4,"area":null},{"id":"2406.19531","title":"Off-policy Evaluation with Deeply-abstracted States","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2410.13743","title":"Single-Timescale Multi-Sequence Stochastic Approximation Without Fixed Point Smoothness: Theories and Applications","created":"2024-10-17","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":"2510.12375","title":"Improved Central Limit Theorem and Bootstrap Approximations for Linear Stochastic Approximation","created":"2025-10-14","cited_by_count":4,"area":null},{"id":"2202.06922","title":"Convex Programs and Lyapunov Functions for Reinforcement Learning: A Unified Perspective on the Analysis of Value-Based Methods","created":"2022-02-14","cited_by_count":3,"area":null}],"next_cursor":"100"}