{"total":30,"rows":[{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2207.00713","title":"q-Learning in Continuous Time","created":"2022-07-02","cited_by_count":91,"area":null},{"id":"2305.18901","title":"Policy Optimization for Continuous Reinforcement Learning","created":"2023-05-30","cited_by_count":31,"area":null},{"id":"2211.00617","title":"Convergence of policy gradient methods for finite-horizon exploratory linear-quadratic control problems","created":"2022-11-01","cited_by_count":25,"area":null},{"id":"2303.10257","title":"Recent Developments in Machine Learning Methods for Stochastic Control and Games","created":"2023-03-17","cited_by_count":24,"area":null},{"id":"2303.06993","title":"Actor-Critic learning for mean-field control in continuous time","created":"2023-03-13","cited_by_count":22,"area":null},{"id":"2306.16208","title":"Continuous-time q-learning for mean-field control problems","created":"2023-06-28","cited_by_count":22,"area":null},{"id":"2311.14168","title":"Fast Policy Learning for Linear Quadratic Control with Entropy Regularization","created":"2023-11-23","cited_by_count":13,"area":null},{"id":"2405.20250","title":"Entropy annealing for policy mirror descent in continuous time and space","created":"2024-05-30","cited_by_count":12,"area":null},{"id":"2411.01302","title":"Regret of exploratory policy improvement and $q$-learning","created":"2024-11-02","cited_by_count":12,"area":null},{"id":"2205.11168","title":"Logarithmic regret bounds for continuous-time average-reward Markov decision processes","created":"2022-05-23","cited_by_count":8,"area":null},{"id":"2203.11758","title":"Linear convergence of a policy gradient method for some finite horizon continuous time control problems","created":"2022-03-22","cited_by_count":7,"area":null},{"id":"2309.04317","title":"Actor critic learning algorithms for mean-field control with moment neural networks","created":"2023-09-08","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":"2208.04466","title":"Optimal scheduling of entropy regulariser for continuous-time linear-quadratic reinforcement learning","created":"2022-08-08","cited_by_count":6,"area":null},{"id":"2309.10953","title":"Deep Reinforcement Learning for Infinite Horizon Mean Field Problems in Continuous Spaces","created":"2023-09-19","cited_by_count":6,"area":null},{"id":"2210.00832","title":"Square-root regret bounds for continuous-time episodic Markov decision processes","created":"2022-10-03","cited_by_count":5,"area":null},{"id":"2312.05880","title":"Data-driven optimal stopping: A pure exploration analysis","created":"2023-12-10","cited_by_count":4,"area":null},{"id":"2503.21224","title":"Efficient Learning for Entropy-Regularized Markov Decision Processes via Multilevel Monte Carlo","created":"2025-03-27","cited_by_count":3,"area":null},{"id":"2208.08497","title":"Choquet regularization for reinforcement learning","created":"2022-08-17","cited_by_count":2,"area":null},{"id":"2312.15385","title":"Discrete-Time Mean-Variance Strategy Based on Reinforcement Learning","created":"2023-12-24","cited_by_count":2,"area":null},{"id":"2410.14788","title":"Polynomial Scaling is Possible For Neural Operator Approximations of Structured Families of BSDEs","created":"2024-10-18","cited_by_count":2,"area":null},{"id":"2509.09135","title":"Continuous-Time Value Iteration for Multi-Agent Reinforcement Learning","created":"2025-09-11","cited_by_count":2,"area":null},{"id":"2212.08949","title":"Managing Temporal Resolution in Continuous Value Estimation: A Fundamental Trade-off","created":"2022-12-17","cited_by_count":1,"area":null},{"id":"2506.08121","title":"Continuous Policy and Value Iteration for Relaxed Stochastic Control Problems and Its Convergence","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2508.05241","title":"Periodic evaluation of defined-contribution pension fund: A dynamic risk measure approach","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2511.17784","title":"A Variance-Based Analysis of Sample Complexity for Grid Coverage","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2604.18972","title":"Beyond Bellman: High-Order Generator Regression for Continuous-Time Policy Evaluation","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2609.14972","title":"Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and Convergence","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2610.04285","title":"Amortized Score-Hamiltonian Policy Iteration: A Grid-Free Scheme for Relaxed Stochastic Control Problems","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}