{"total":101,"rows":[{"id":"2312.11752","title":"Learning a Diffusion Model Policy from Rewards via Q-Score Matching","created":"2023-12-18","cited_by_count":138,"area":"diffusion"},{"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":"2402.07487","title":"Score-based Diffusion Models via Stochastic Differential Equations -- a Technical Tutorial","created":"2024-02-12","cited_by_count":60,"area":"diffusion"},{"id":"2502.01819","title":"Score as Action: Fine-Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning","created":"2025-02-03","cited_by_count":33,"area":"diffusion"},{"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":"2409.04832","title":"Reward-Directed Score-Based Diffusion Models via q-Learning","created":"2024-09-07","cited_by_count":19,"area":"diffusion"},{"id":"2409.08400","title":"Scores as Actions: a framework of fine-tuning diffusion models by continuous-time reinforcement learning","created":"2024-09-12","cited_by_count":19,"area":"diffusion"},{"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":"2407.04521","title":"Unified continuous-time q-learning for mean-field game and mean-field control problems","created":"2024-07-05","cited_by_count":13,"area":"deeprl"},{"id":"2503.09981","title":"Accuracy of Discretely Sampled Stochastic Policies in Continuous-time Reinforcement Learning","created":"2025-03-13","cited_by_count":13,"area":"deeprl"},{"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":"2407.17226","title":"Sublinear Regret for a Class of Continuous-Time Linear-Quadratic Reinforcement Learning Problems","created":"2024-07-24","cited_by_count":12,"area":"deeprl"},{"id":"2411.01302","title":"Regret of exploratory policy improvement and $q$-learning","created":"2024-11-02","cited_by_count":12,"area":null},{"id":"2404.12598","title":"Continuous-time Risk-sensitive Reinforcement Learning via Quadratic Variation Penalty","created":"2024-04-19","cited_by_count":9,"area":"deeprl"},{"id":"2408.09242","title":"Learning to Optimally Stop Diffusion Processes, with Financial Applications","created":"2024-08-17","cited_by_count":9,"area":"deeprl"},{"id":"2408.09335","title":"Exploratory Optimal Stopping: A Singular Control Formulation","created":"2024-08-18","cited_by_count":9,"area":"deeprl"},{"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":"2404.17939","title":"Control randomisation approach for policy gradient and application to reinforcement learning in optimal switching","created":"2024-04-27","cited_by_count":8,"area":"deeprl"},{"id":"2407.03888","title":"Continuous-time q-Learning for Jump-Diffusion Models under Tsallis Entropy","created":"2024-07-04","cited_by_count":8,"area":"deeprl"},{"id":"2509.23711","title":"Deterministic Policy Gradient for Reinforcement Learning with Continuous Time and State","created":"2025-09-28","cited_by_count":8,"area":"deeprl"},{"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":"2410.11022","title":"Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning","created":"2024-10-14","cited_by_count":7,"area":"deeprl"},{"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":"2405.12535","title":"PhiBE: A PDE-based Bellman Equation for Continuous Time Policy Evaluation","created":"2024-05-21","cited_by_count":6,"area":"deeprl"},{"id":"2512.04697","title":"Continuous-time reinforcement learning for optimal switching over multiple regimes","created":"2025-12-04","cited_by_count":6,"area":"deeprl"},{"id":"2604.27372","title":"Continuous-time q-learning for mean-field control with common noise, part-I: Theoretical foundations","created":"2026-04-30","cited_by_count":6,"area":"deeprl"},{"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":"2407.10065","title":"An Efficient High-Dimensional Gradient Estimator for Stochastic Differential Equations","created":"2024-07-14","cited_by_count":4,"area":"deeprl"},{"id":"2510.17122","title":"Continuous Q-Score Matching: Diffusion Guided Reinforcement Learning for Continuous-Time Control","created":"2025-10-20","cited_by_count":4,"area":"deeprl"},{"id":"2601.18681","title":"ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule","created":"2026-01-26","cited_by_count":4,"area":"diffusion"},{"id":"2604.27378","title":"Continuous-time q-learning for mean-field control with common noise, part-II: q-learning algorithms","created":"2026-04-30","cited_by_count":4,"area":"deeprl"},{"id":"2605.20718","title":"Policy Gradient for Continuous-Time Mean-Field Control","created":"2026-05-20","cited_by_count":4,"area":"deeprl"},{"id":"2406.05358","title":"Reinforcement Learning for Intensity Control: An Application to Choice-Based Network Revenue Management","created":"2024-06-08","cited_by_count":3,"area":"deeprl"},{"id":"2410.07778","title":"On the grid-sampling limit SDE","created":"2024-10-10","cited_by_count":3,"area":"deeprl"},{"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":"2505.15544","title":"A Temporal Difference Method for Stochastic Continuous Dynamics","created":"2025-05-21","cited_by_count":3,"area":"deeprl"},{"id":"2507.00358","title":"Data-Driven Exploration for a Class of Continuous-Time Indefinite Linear--Quadratic Reinforcement Learning Problems","created":"2025-07-01","cited_by_count":3,"area":"deeprl"},{"id":"2507.06428","title":"Neural Actor-Critic Methods for Hamilton-Jacobi-Bellman PDEs: Asymptotic Analysis and Numerical Studies","created":"2025-07-08","cited_by_count":3,"area":"deeprl"},{"id":"2507.20853","title":"Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces","created":"2025-07-28","cited_by_count":3,"area":"deeprl"},{"id":"2606.11798","title":"Deterministic Policy Gradient for Learning Equilibrium in Time-Inconsistent Control Problems","created":"2026-06-10","cited_by_count":3,"area":"deeprl"},{"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":"2405.16449","title":"Reinforcement Learning for Jump-Diffusions, with Financial Applications","created":"2024-05-26","cited_by_count":2,"area":"deeprl"},{"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":"2411.11697","title":"Robust Reinforcement Learning under Diffusion Models for Data with Jumps","created":"2024-11-18","cited_by_count":2,"area":"diffusion"},{"id":"2506.22203","title":"A Reinforcement Learning Framework for Some Singular Stochastic Control Problems","created":"2025-06-27","cited_by_count":2,"area":"deeprl"},{"id":"2509.09135","title":"Continuous-Time Value Iteration for Multi-Agent Reinforcement Learning","created":"2025-09-11","cited_by_count":2,"area":null},{"id":"2604.21179","title":"Discretization error from regularized Reinforcement Learning to continuous-time stochastic control","created":"2026-04-23","cited_by_count":2,"area":"deeprl"},{"id":"2607.14522","title":"A Continuous-Time Reinforcement Learning Framework for Fine-Tuning Discrete Diffusion Models","created":"2026-07-16","cited_by_count":2,"area":"diffusion"},{"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":"2409.17200","title":"A random measure approach to reinforcement learning in continuous time","created":"2024-09-25","cited_by_count":1,"area":"deeprl"},{"id":"2502.01269","title":"Exploratory Utility Maximization Problem with Tsallis Entropy","created":"2025-02-03","cited_by_count":1,"area":"deeprl"},{"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":"2512.02769","title":"Reinforcement learning for irreversible reinsurance problems: the randomized singular control approach","created":"2025-12-02","cited_by_count":1,"area":"deeprl"},{"id":"2601.19299","title":"Continuous-time q-learning for Markov regime switching system under Tsallis entropy","created":"2026-01-27","cited_by_count":1,"area":"deeprl"},{"id":"2603.00738","title":"Exploratory Randomization for Discrete-Time Risk-Sensitive Benchmarked Investment Management with Reinforcement Learning","created":"2026-02-28","cited_by_count":1,"area":"deeprl"},{"id":"2605.13010","title":"Amortized Guidance for Image Inpainting with Pretrained Diffusion Models","created":"2026-05-13","cited_by_count":1,"area":"diffusion"},{"id":"2606.26498","title":"Mean-Field PhiBE: Continuous-Time Mean-Field Reinforcement Learning from Discrete-Time Data","created":"2026-06-25","cited_by_count":1,"area":"deeprl"},{"id":"2606.28671","title":"Entropy-Regularized Reinforcement Learning for Linear-Quadratic Stackelberg Differential Games in Regime-Switching Diffusion Models","created":"2026-06-27","cited_by_count":1,"area":"deeprl"},{"id":"2607.11005","title":"Actor-Critic Learning for Extended Mean Field Control with Deterministic Policies","created":"2026-07-13","cited_by_count":1,"area":"deeprl"},{"id":"2402.04721","title":"Robust policy iteration for continuous-time stochastic $H_\\infty$ control problem with unknown dynamics","created":"2024-02-07","cited_by_count":0,"area":"deeprl"},{"id":"2404.11382","title":"Convergence of Policy Gradient for Stochastic Linear-Quadratic Control Problem in Infinite Horizon","created":"2024-04-17","cited_by_count":0,"area":"deeprl"},{"id":"2411.06645","title":"Two Kinds of Learning Algorithms for Continuous-Time VWAP Targeting Execution","created":"2024-11-11","cited_by_count":0,"area":"deeprl"},{"id":"2501.17801","title":"Consensus Based Stochastic Control","created":"2025-01-29","cited_by_count":0,"area":"deeprl"},{"id":"2502.04788","title":"A non-zero-sum game with reinforcement learning under mean-variance framework","created":"2025-02-07","cited_by_count":0,"area":"deeprl"},{"id":"2502.14141","title":"A hierarchical resource-efficient deep policy gradient method for continuous-time optimal control problems","created":"2025-02-19","cited_by_count":0,"area":"deeprl"},{"id":"2504.01482","title":"A Robust Model-Based Approach for Continuous-Time Policy Evaluation with Unknown L\\'evy Process Dynamics","created":"2025-04-02","cited_by_count":0,"area":"deeprl"},{"id":"2506.13207","title":"Research on Optimal Control Problem Based on Reinforcement Learning under Knightian Uncertainty","created":"2025-06-16","cited_by_count":0,"area":"deeprl"},{"id":"2507.15234","title":"An Optimization-Based Framework for Solving Forward-Backward Stochastic Differential Equations: Convergence Analysis and Error Bounds","created":"2025-07-21","cited_by_count":0,"area":"deeprl"},{"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":"2510.10260","title":"Robust Exploratory Stopping under Ambiguity in Reinforcement Learning","created":"2025-10-11","cited_by_count":0,"area":"deeprl"},{"id":"2510.19950","title":"Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty Sets","created":"2025-10-22","cited_by_count":0,"area":"deeprl"},{"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":"2512.02386","title":"Risk-Sensitive Q-Learning in Continuous Time with Application to Dynamic Portfolio Selection","created":"2025-12-02","cited_by_count":0,"area":"deeprl"},{"id":"2512.09224","title":"Exploratory Mean-Variance with Jumps: An Equilibrium Approach","created":"2025-12-10","cited_by_count":0,"area":"deeprl"},{"id":"2601.20387","title":"Reinforcement Learning for Dividend Optimization in Partially Observed Regime-Switching Diffusion Model","created":"2026-01-28","cited_by_count":0,"area":"deeprl"},{"id":"2602.06930","title":"Continuous-time reinforcement learning: ellipticity enables model-free value function approximation","created":"2026-02-06","cited_by_count":0,"area":"deeprl"},{"id":"2602.08075","title":"Reinforcement Learning Method for Zero-Sum Linear-Quadratic Stochastic Differential Games in Infinite Horizons","created":"2026-02-08","cited_by_count":0,"area":"deeprl"},{"id":"2604.02035","title":"Reinforcement Learning for Speculative Trading under Exploratory Framework","created":"2026-04-02","cited_by_count":0,"area":"deeprl"},{"id":"2604.05398","title":"An Actor-Critic Framework for Continuous-Time Jump-Diffusion Controls with Normalizing Flows","created":"2026-04-07","cited_by_count":0,"area":"deeprl"},{"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":"2605.18246","title":"Privacy Preserving Reinforcement Learning with One-Sided Feedback","created":"2026-05-18","cited_by_count":0,"area":"deeprl"},{"id":"2606.04335","title":"Policy Gradient for Continuous-Time Robust Markov Decision Processes","created":"2026-06-03","cited_by_count":0,"area":"deeprl"},{"id":"2606.12875","title":"Randomized Optimal Switching Problem and Related Mirror Descent Flow","created":"2026-06-11","cited_by_count":0,"area":"deeprl"},{"id":"2606.20903","title":"Reinforcement Learning for Risk-Sensitive Investment Management: a Free Energy--Entropy Duality Approach","created":"2026-06-18","cited_by_count":0,"area":"deeprl"},{"id":"2606.21925","title":"PhiBE-Q-Learning: Bridging Off-Policy Reinforcement Learning and Continuous-Time Control","created":"2026-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2607.02137","title":"ART for Diffusion Sampling: Continuous-Time Control and Actor-Critic Learning","created":"2026-07-02","cited_by_count":0,"area":"diffusion"},{"id":"2607.03168","title":"Entropy Regularization Improves Policy Robustness in Continuous-Time Reinforcement Learning","created":"2026-07-03","cited_by_count":0,"area":"deeprl"},{"id":"2607.16625","title":"Dynamic mean-variance portfolio selection with no-shorting constraints and unknown investment opportunity sets","created":"2026-07-18","cited_by_count":0,"area":"deeprl"},{"id":"2607.19928","title":"Continuous-Time Reinforcement Learning for $N$-Player Stochastic Differential Games with Exploratory Policies","created":"2026-07-22","cited_by_count":0,"area":"deeprl"},{"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}],"next_cursor":"100"}