Near-continuous time reinforcement learning for continuous state-action spaces

MaRDI QIDQ7017106zbMATH OpenFDO

Authors Lorenzo Croissant, Marc Abeille, Bruno Bouchard

Publication date 6 March 2025

Full work available at URL https://proceedings.mlr.press/v237/croissant24a.html

zbMATH Keywords

continuous state spacediffusion approximationeluder dimensiononline reinforcement learningoptimism in the face of uncertaintystochastic control

Mathematics Subject Classification ID

Stochastic learning and adaptive control (93E35)

Cites work

• Algorithms for reinforcement learning.
• Bandit algorithms
• Concentration inequalities. A nonasymptotic theory of independence
• Consistency of Generalized Finite Difference Schemes for the Stochastic HJB Equation
• Elliptic Partial Differential Equations of Second Order
• Ergodic control of diffusion processes.
• Financial Modelling with Jump Processes
• Finite-time analysis of the multiarmed bandit problem
• scientific article; zbMATH DE number 1577097 (Why is no real title available?)
• scientific article; zbMATH DE number 1631026 (Why is no real title available?)
• scientific article; zbMATH DE number 4205918 (Why is no real title available?)
• scientific article; zbMATH DE number 49190 (Why is no real title available?)
• scientific article; zbMATH DE number 802915 (Why is no real title available?)
• scientific article; zbMATH DE number 1433619 (Why is no real title available?)
• scientific article; zbMATH DE number 5685899 (Why is no real title available?)
• Linear and quasilinear elliptic equations
• Near-optimal regret bounds for reinforcement learning
• Numerical Methods for Elliptic and Parabolic Partial Differential Equations
• On ergodic stochastic control
• Optimal control of diffusion processes and hamilton–jacobi–bellman equations part 2 : viscosity solutions and uniqueness
• Optimal Real-Time Bidding Strategies
• Probability methods for approximations in stochastic control and for elliptic equations
• Stochastic stability of differential equations. With contributions by G. N. Milstein and M. B. Nevelson

Cited in

(1)

• Diffusive limit approximation of pure jump optimal ergodic control problems

This page was built for publication: Near-continuous time reinforcement learning for continuous state-action spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7017106)