{"total":22,"rows":[{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2111.11232","title":"Policy Gradient and Actor-Critic Learning in Continuous Time and Space: Theory and Algorithms","created":"2021-11-22","cited_by_count":101,"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":"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":"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":"2312.11797","title":"Data-Driven Merton's Strategies via Policy Randomization","created":"2023-12-19","cited_by_count":8,"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":"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":"2406.10920","title":"Hamilton-Jacobi Based Policy-Iteration via Deep Operator Learning","created":"2024-06-16","cited_by_count":5,"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":"2410.14839","title":"Multi-Task Dynamic Pricing in Credit Market with Contextual Information","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":"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":"2607.29593","title":"Convergence and Regret of the Policy Gradient for Multi-Armed Bandits in Diffusion Environment","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.10777","title":"Path Integral Value Matching for Linear Quadratic Stochastic Optimal Control","created":"2026-08-11","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}