Optimal Scheduling of Entropy Regularizer for Continuous-Time Linear-Quadratic Reinforcement Learning

DOI10.1137/22m1515744arXiv2208.04466WikidataQ129754889 ScholiaQ129754889MaRDI QIDQ6180253

Lukasz Szpruch, Tanut Treetanthiploet, Yu-Fei Zhang

Publication date: 19 January 2024

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

Full work available at URL: https://arxiv.org/abs/2208.04466

zbMATH Keywords

linear-quadraticentropy regularizationregret analysiscontinuous-time reinforcement learningexploratory controlproximal policy update

Mathematics Subject Classification ID

Linear-quadratic optimal control problems (49N10) Stochastic learning and adaptive control (93E35) Sequential statistical design (62L05) Measures of information, entropy (94A17)

Cites Work

• Mirror descent and nonlinear projected subgradient methods for convex optimization.
• Reinforcement learning and stochastic optimisation
• Exploratory LQG mean field games with entropy regularization
• On the sample complexity of the linear quadratic regulator
• A modified MSA for stochastic control problems
• The exact law of large numbers via Fubini extension and characterization of insurable risks
• Regularity and Stability of Feedback Relaxed Controls
• Adaptive continuous-time linear quadratic Gaussian control
• High-Dimensional Probability
• Compactification methods in the control of degenerate diffusions: existence of an optimal control
• On Incomplete Learning and Certainty-Equivalence Control
• Continuous‐time mean–variance portfolio selection: A reinforcement learning framework
• Entropy Regularization for Mean Field Games with Learning
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Optimal Scheduling of Entropy Regularizer for Continuous-Time Linear-Quadratic Reinforcement Learning