Sublinear regret for a class of continuous-time linear-quadratic reinforcement learning problems

DOI10.1137/24M1695075MaRDI QIDQ6925757zbMATH OpenFDO

Authors Yilie Huang, Yanwei Jia, Xun Yu Zhou

Publication date 25 September 2025

Published in SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/24M1695075

zbMATH Keywords

continuous-time reinforcement learningexploration schedulingmodel-free policy gradientregret boundsreinforcement learning algorithmstochastic linear-quadratic control

Mathematics Subject Classification ID

Linear-quadratic optimal control problems (49N10) Learning and adaptive systems in artificial intelligence (68T05) Optimal stochastic control (93E20)

Cites work

• A Stochastic Approximation Algorithm with Varying Bounds
• A Stochastic Approximation Method
• Continuous-time mean-variance portfolio selection: a stochastic LQ framework
• Convergence of policy gradient methods for finite-horizon exploratory linear-quadratic control problems
• Fast global convergence of natural policy gradient methods with entropy regularization
• General bounds and finite-time improvement for the Kiefer-Wolfowitz stochastic approximation algorithm
• scientific article; zbMATH DE number 54145 (Why is no real title available?)
• scientific article; zbMATH DE number 1325009 (Why is no real title available?)
• scientific article; zbMATH DE number 7626721 (Why is no real title available?)
• scientific article; zbMATH DE number 7307478 (Why is no real title available?)
• Learning equilibrium mean‐variance strategy
• Linear matrix inequalities, Riccati equations, and indefinite stochastic linear quadratic controls
• Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem
• Optimal Scheduling of Entropy Regularizer for Continuous-Time Linear-Quadratic Reinforcement Learning
• Policy gradient in continuous time
• Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon
• Policy iterations for reinforcement learning problems in continuous time and space -- fundamental theory and methods
• Reinforcement learning. An introduction
• Stochastic Linear Quadratic Regulators with Indefinite Control Weight Costs

Cited in

(1)

• Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and Convergence

This page was built for publication: Sublinear regret for a class of continuous-time linear-quadratic reinforcement learning problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6925757)