Convergence of policy gradient methods for finite-horizon exploratory linear-quadratic control problems

DOI10.1137/22M1533517MaRDI QIDQ6490237

Christoph Reisinger, Michael Giegrich, zbMATH Open Web Interface contents unavailable due to conflicting licenses.

Publication date: 23 April 2024

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

zbMATH Keywords

global linear convergencemesh-independent convergencepolicy optimizationcontinuous-time linear-quadratic controlgeometry-aware gradientrelative Entropy

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Optimal stochastic control (93E20)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Linear quadratic mean field type control and mean field games with common noise, with application to production of an exhaustible resource
• Continuous-time mean-variance portfolio selection: a stochastic LQ framework
• Exploratory LQG mean field games with entropy regularization
• A theoretical and empirical comparison of gradient approximations in derivative-free optimization
• Open-Loop and Closed-Loop Solvabilities for Stochastic Linear Quadratic Optimal Control Problems
• Algorithmic Trading, Stochastic Control, and Mutually Exciting Processes
• Learning Optimal Controllers for Linear Systems With Multiplicative Noise via Policy Gradient
• Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon
• Policy Optimization for $\mathcal{H}_2$ Linear Control with $\mathcal{H}_\infty$ Robustness Guarantee: Implicit Regularization and Global Convergence
• Continuous‐time mean–variance portfolio selection: A reinforcement learning framework

This page was built for publication: Convergence of policy gradient methods for finite-horizon exploratory linear-quadratic control problems