Continuous time reinforcement learning: a random measure approach

DOI10.1016/J.SPA.2025.104848MaRDI QIDQ6873533zbMATH OpenFDO

Authors Christian Bender, Nguyen Tran Thuan

Publication date 16 January 2026

Published in Stochastic Processes and their Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.SPA.2025.104848

zbMATH Keywords

exploratory controlrandom measuresreinforcement learningstochastic differential equationsweak convergence

Mathematics Subject Classification ID

Spaces of measures, convergence of measures (28A33) Convergence of probability measures (60B10) Central limit and other weak theorems (60F05) Random measures (60G57) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Feedback control (93B52) Stochastic learning and adaptive control (93E35)

Cites work

• A Stochastic Approximation Method
• Actor-critic learning for mean-field control in continuous time
• Choquet Regularization for Continuous-Time Reinforcement Learning
• Continuous‐time mean–variance portfolio selection: A reinforcement learning framework
• Convergence of policy gradient methods for finite-horizon exploratory linear-quadratic control problems
• Entropy Regularization for Mean Field Games with Learning
• Exploratory Control with Tsallis Entropy for Latent Factor Models
• Exploratory HJB equations and their convergence
• Exploratory LQG mean field games with entropy regularization
• scientific article; zbMATH DE number 1577097 (Why is no real title available?)
• scientific article; zbMATH DE number 3984248 (Why is no real title available?)
• scientific article; zbMATH DE number 43057 (Why is no real title available?)
• scientific article; zbMATH DE number 51724 (Why is no real title available?)
• scientific article; zbMATH DE number 140600 (Why is no real title available?)
• scientific article; zbMATH DE number 1354815 (Why is no real title available?)
• scientific article; zbMATH DE number 1834045 (Why is no real title available?)
• scientific article; zbMATH DE number 765034 (Why is no real title available?)
• scientific article; zbMATH DE number 7307478 (Why is no real title available?)
• scientific article; zbMATH DE number 2220058 (Why is no real title available?)
• Individual risk and Lebesgue extension without aggregate uncertainty
• Learning equilibrium mean‐variance strategy
• Limit theorems of Hilbert valued semimartingales and Hilbert valued martingale measures
• Martingale measures and stochastic calculus
• Optimal Scheduling of Entropy Regularizer for Continuous-Time Linear-Quadratic Reinforcement Learning
• Random measures, theory and applications
• Regularity and stability of feedback relaxed controls
• Reinforcement learning for continuous-time mean-variance portfolio selection in a regime-switching market
• Reinforcement learning. An introduction
• Strong solutions for SPDE with locally monotone coefficients driven by Lévy noise
• The exact law of large numbers via Fubini extension and characterization of insurable risks
• Vague convergence of locally integrable martingale measures

Cited in

(1)

• Accuracy of discretely sampled stochastic policies in continuous-time reinforcement learning

This page was built for publication: Continuous time reinforcement learning: a random measure approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6873533)