{"total":85,"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":"2207.00713","title":"q-Learning in Continuous Time","created":"2022-07-02","cited_by_count":91,"area":null},{"id":"2101.08862","title":"Breaking the Deadly Triad with a Target Network","created":"2021-01-21","cited_by_count":47,"area":null},{"id":"2210.01808","title":"Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees","created":"2022-10-04","cited_by_count":42,"area":"offlinerl"},{"id":"2105.04646","title":"Deeply-Debiased Off-Policy Interval Estimation","created":"2021-05-10","cited_by_count":36,"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":"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":"2109.14756","title":"A Two-Time-Scale Stochastic Optimization Framework with Applications in Control and Reinforcement Learning","created":"2021-09-29","cited_by_count":24,"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":"2110.10351","title":"Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process","created":"2021-10-20","cited_by_count":19,"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":"2110.11383","title":"Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processes","created":"2021-10-21","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":"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":"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":"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":"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":"2211.15956","title":"Offline Reinforcement Learning with Closed-Form Policy Improvement Operators","created":"2022-11-29","cited_by_count":14,"area":"offlinerl"},{"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":"2210.01282","title":"Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees","created":"2022-10-04","cited_by_count":12,"area":"offlinerl"},{"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":"2108.05338","title":"Truncated Emphatic Temporal Difference Methods for Prediction and Control","created":"2021-08-11","cited_by_count":10,"area":null},{"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":"2405.09660","title":"Fast Two-Time-Scale Stochastic Gradient Method with Applications in Reinforcement Learning","created":"2024-05-15","cited_by_count":10,"area":"deeprl"},{"id":"2206.12848","title":"Analysis of Stochastic Processes through Replay Buffers","created":"2022-06-26","cited_by_count":9,"area":null},{"id":"2207.10839","title":"Robust Knowledge Adaptation for Dynamic Graph Neural Networks","created":"2022-07-22","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":"2505.15138","title":"Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm","created":"2025-05-21","cited_by_count":8,"area":"deeprl"},{"id":"2103.16377","title":"Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved Complexity","created":"2021-03-30","cited_by_count":7,"area":null},{"id":"2110.00445","title":"Sim and Real: Better Together","created":"2021-10-01","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":"2511.03618","title":"Towards Formalizing Reinforcement Learning Theory: A Robbins-Siegmund Approach","created":"2025-11-05","cited_by_count":7,"area":"deeprl"},{"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":"2105.12545","title":"Successive Convex Approximation Based Off-Policy Optimization for Constrained Reinforcement Learning","created":"2021-05-26","cited_by_count":5,"area":null},{"id":"2111.00185","title":"Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings","created":"2021-10-30","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":"2405.08005","title":"Graphon Mean Field Games with a Representative Player: Analysis and Learning Algorithm","created":"2024-05-08","cited_by_count":5,"area":null},{"id":"2405.15920","title":"SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning","created":"2024-05-24","cited_by_count":5,"area":"deeprl"},{"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":"2409.12135","title":"Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features","created":"2024-09-18","cited_by_count":5,"area":"deeprl"},{"id":"2503.08934","title":"Near-Optimal Sample Complexity for Iterated CVaR Reinforcement Learning with a Generative Model","created":"2025-03-11","cited_by_count":5,"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":"2509.26442","title":"Extensions of Robbins-Siegmund Theorem with Applications in Reinforcement Learning","created":"2025-09-30","cited_by_count":5,"area":"deeprl"},{"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":"2205.13617","title":"Does DQN Learn?","created":"2022-05-26","cited_by_count":4,"area":null},{"id":"2206.01666","title":"Algorithm for Constrained Markov Decision Process with Linear Convergence","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2405.04017","title":"An Improved Finite-time Analysis of Temporal Difference Learning with Deep Neural Networks","created":"2024-05-07","cited_by_count":4,"area":"deeprl"},{"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":"2209.02555","title":"Finite-Time Error Bounds for Greedy-GQ","created":"2022-09-06","cited_by_count":3,"area":null},{"id":"2512.06244","title":"Auto-exploration for online reinforcement learning","created":"2025-12-06","cited_by_count":3,"area":"deeprl"},{"id":"2110.08902","title":"On the Convergence of Experience Replay in Policy Optimization: Characterizing Bias, Variance, and Finite-Time Convergence","created":"2021-10-17","cited_by_count":2,"area":null},{"id":"2306.11271","title":"Warm-Start Actor-Critic: From Approximation Error to Sub-optimality Gap","created":"2023-06-20","cited_by_count":2,"area":null},{"id":"2403.05979","title":"Enhancing Classification Performance via Reinforcement Learning for Feature Selection","created":"2024-03-09","cited_by_count":2,"area":"deeprl"},{"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":"2510.06149","title":"Implicit Updates for Average-Reward Temporal Difference Learning","created":"2025-10-07","cited_by_count":2,"area":"deeprl"},{"id":"2512.17688","title":"Convergence Guarantees for Federated SARSA with Local Training and Heterogeneous Agents","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2602.11800","title":"Temporal Difference Learning with Constrained Initial Representations","created":"2026-02-12","cited_by_count":2,"area":"deeprl"},{"id":"2602.16629","title":"Almost Sure Convergence of Differential Temporal Difference Learning for Average Reward Markov Decision Processes","created":"2026-02-18","cited_by_count":2,"area":"deeprl"},{"id":"2104.09620","title":"Predictor-Corrector(PC) Temporal Difference(TD) Learning (PCTD)","created":"2021-04-15","cited_by_count":1,"area":null},{"id":"2111.12665","title":"Finite-Time Error Bounds for Distributed Linear Stochastic Approximation","created":"2021-11-24","cited_by_count":1,"area":null},{"id":"2208.12341","title":"Variance Reduction based Experience Replay for Policy Optimization","created":"2022-08-25","cited_by_count":1,"area":null},{"id":"2301.00521","title":"A Policy Optimization Method Towards Optimal-time Stability","created":"2023-01-02","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":"2312.11863","title":"Neural Network Approximation for Pessimistic Offline Reinforcement Learning","created":"2023-12-19","cited_by_count":1,"area":"offlinerl"},{"id":"2503.17865","title":"Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality","created":"2025-03-22","cited_by_count":1,"area":"offlinerl"},{"id":"2504.03721","title":"A Hybrid Reinforcement Learning Framework for Hard Latency Constrained Resource Scheduling","created":"2025-03-30","cited_by_count":1,"area":"deeprl"},{"id":"2509.15392","title":"Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis","created":"2025-09-18","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":"2302.13087","title":"Gauss-Newton Temporal Difference Learning with Nonlinear Function Approximation","created":"2023-02-25","cited_by_count":0,"area":null},{"id":"2306.06402","title":"A Single-Loop Deep Actor-Critic Algorithm for Constrained Reinforcement Learning with Provable Convergence","created":"2023-06-10","cited_by_count":0,"area":null},{"id":"2310.17915","title":"Lifting the Veil: Unlocking the Power of Depth in Q-learning","created":"2023-10-27","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":"2408.06945","title":"Heavy-Ball Momentum Accelerated Actor-Critic With Function Approximation","created":"2024-08-13","cited_by_count":0,"area":"deeprl"},{"id":"2504.16415","title":"Natural Policy Gradient for Average Reward Non-Stationary RL","created":"2025-04-23","cited_by_count":0,"area":"deeprl"},{"id":"2510.03912","title":"Generalized Fitted Q-Iteration with Clustered Data","created":"2025-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2601.18907","title":"Implicit Q-Learning and SARSA: Liberating Policy Control from Step-Size Calibration","created":"2026-01-26","cited_by_count":0,"area":"deeprl"},{"id":"2603.00043","title":"Reinforcement Learning for Control with Probabilistic Stability Guarantee: A Finite-Sample Approach","created":"2026-02-09","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":"2609.18782","title":"A Convergence Framework for Deep $V$-Learning: Error Propagation and Sharp Action-Gap Bounds","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}