{"total":34,"rows":[{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2209.05423","title":"Statistical Learning Theory for Control: A Finite Sample Perspective","created":"2022-09-12","cited_by_count":53,"area":null},{"id":"2107.13090","title":"Policy Gradient Methods Find the Nash Equilibrium in N-player General-sum Linear-quadratic Games","created":"2021-07-27","cited_by_count":25,"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":"2203.02591","title":"A Small Gain Analysis of Single Timescale Actor Critic","created":"2022-03-04","cited_by_count":24,"area":null},{"id":"2112.13414","title":"Reinforcement Learning with Dynamic Convex Risk Measures","created":"2021-12-26","cited_by_count":21,"area":null},{"id":"2101.01041","title":"Derivative-Free Policy Optimization for Linear Risk-Sensitive and Robust Control Design: Implicit Regularization and Sample Complexity","created":"2021-01-04","cited_by_count":15,"area":null},{"id":"2307.11436","title":"Neural Operators for PDE Backstepping Control of First-Order Hyperbolic PIDE with Recycle and Delay","created":"2023-07-21","cited_by_count":13,"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":"2102.12608","title":"Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with $\\sqrt{T}$ Regret","created":"2021-02-25","cited_by_count":12,"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":"2302.13144","title":"Revisiting LQR Control from the Perspective of Receding-Horizon Policy Gradient","created":"2023-02-25","cited_by_count":10,"area":null},{"id":"2301.12624","title":"Learning the Kalman Filter with Fine-Grained Sample Complexity","created":"2023-01-30","cited_by_count":9,"area":null},{"id":"2310.02671","title":"Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods","created":"2023-10-04","cited_by_count":9,"area":null},{"id":"2503.21422","title":"From Deep Learning to LLMs: A survey of AI in Quantitative Investment","created":"2025-03-27","cited_by_count":9,"area":null},{"id":"2109.06362","title":"Theoretical Guarantees of Fictitious Discount Algorithms for Episodic Reinforcement Learning and Global Convergence of Policy Gradient Methods","created":"2021-09-13","cited_by_count":7,"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":"2210.11577","title":"Global Convergence of Direct Policy Search for State-Feedback $\\mathcal{H}_\\infty$ Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential","created":"2022-10-20","cited_by_count":7,"area":null},{"id":"2210.04810","title":"Towards a Theoretical Foundation of Policy Optimization for Learning Control Policies","created":"2022-10-10","cited_by_count":6,"area":null},{"id":"2311.18736","title":"Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithms","created":"2023-11-30","cited_by_count":6,"area":null},{"id":"2303.08431","title":"Policy Gradient Converges to the Globally Optimal Policy for Nearly Linear-Quadratic Regulators","created":"2023-03-15","cited_by_count":5,"area":null},{"id":"2202.06637","title":"Continuous-time stochastic gradient descent for optimizing over the stationary distribution of stochastic differential equations","created":"2022-02-14","cited_by_count":4,"area":null},{"id":"2309.04272","title":"Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last-Iterate Convergence","created":"2023-09-08","cited_by_count":4,"area":null},{"id":"2309.04831","title":"Global Convergence of Receding-Horizon Policy Search in Learning Estimator Designs","created":"2023-09-09","cited_by_count":4,"area":null},{"id":"2310.19022","title":"Optimization Landscape of Policy Gradient Methods for Discrete-time Static Output Feedback","created":"2023-10-29","cited_by_count":4,"area":null},{"id":"2206.14267","title":"Applications of Reinforcement Learning in Finance -- Trading with a Double Deep Q-Network","created":"2022-06-28","cited_by_count":2,"area":null},{"id":"2303.12785","title":"Matryoshka Policy Gradient for Entropy-Regularized RL: Convergence and Global Optimality","created":"2023-03-22","cited_by_count":2,"area":null},{"id":"2209.05042","title":"On the Optimization Landscape of Dynamic Output Feedback: A Case Study for Linear Quadratic Regulator","created":"2022-09-12","cited_by_count":1,"area":null},{"id":"2405.17370","title":"Model-Agnostic Zeroth-Order Policy Optimization for Meta-Learning of Ergodic Linear Quadratic Regulators","created":"2024-05-27","cited_by_count":1,"area":null},{"id":"2303.16548","title":"Policy Gradient Methods for Discrete Time Linear Quadratic Regulator With Random Parameters","created":"2023-03-29","cited_by_count":0,"area":null},{"id":"2402.11654","title":"Model-Free $\\mu$-Synthesis: A Nonsmooth Optimization Perspective","created":"2024-02-18","cited_by_count":0,"area":null},{"id":"2502.14210","title":"Sample Complexity of Linear Quadratic Regulator Without Initial Stability","created":"2025-02-20","cited_by_count":0,"area":null},{"id":"2506.01816","title":"An adaptive data sampling strategy for stabilizing dynamical systems via controller inference","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2608.07433","title":"Wasserstein Policy Gradient for Entropy-Regularized Linear-Quadratic Control","created":"2026-08-07","cited_by_count":0,"area":null}],"next_cursor":null}