{"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":"2305.18901","title":"Policy Optimization for Continuous Reinforcement Learning","created":"2023-05-30","cited_by_count":31,"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":"2104.09311","title":"Reinforcement learning for linear-convex models with jumps via stability analysis of feedback controls","created":"2021-04-19","cited_by_count":24,"area":null},{"id":"2310.19848","title":"Efficient Exploration in Continuous-time Model-based Reinforcement Learning","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2112.10264","title":"Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models","created":"2021-12-19","cited_by_count":21,"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":"2107.07788","title":"Reinforcement Learning for Adaptive Optimal Stationary Control of Linear Stochastic Systems","created":"2021-07-16","cited_by_count":8,"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":"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":"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":"2301.05157","title":"Statistical Learning with Sublinear Regret of Propagator Models","created":"2023-01-12","cited_by_count":5,"area":null},{"id":"2311.06639","title":"Data-driven rules for multidimensional reflection problems","created":"2023-11-11","cited_by_count":5,"area":null},{"id":"2112.15094","title":"Bayesian Algorithms Learn to Stabilize Unknown Continuous-Time Systems","created":"2021-12-30","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":"2410.03221","title":"Learning to steer with Brownian noise","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2109.07630","title":"Reinforcement Learning Policies in Continuous-Time Linear Systems","created":"2021-09-16","cited_by_count":0,"area":null},{"id":"2206.04434","title":"Regret Analysis of Certainty Equivalence Policies in Continuous-Time Linear-Quadratic Systems","created":"2022-06-09","cited_by_count":0,"area":null},{"id":"2409.11327","title":"On the Effect of Instability on Learning Continuous-Time Linear Control Systems","created":"2024-09-17","cited_by_count":0,"area":null},{"id":"2603.02356","title":"Learning Optimal Search Strategies","created":"2026-03-02","cited_by_count":0,"area":null}],"next_cursor":null}