Approximate Q Learning for Controlled Diffusion Processes and Its Near Optimality

DOI10.1137/22m1484201zbMath1521.93214arXiv2203.07499OpenAlexW4385162439MaRDI QIDQ6136230

Ali Devran Kara, Erhan Bayraktar

Publication date: 29 August 2023

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2203.07499

zbMATH Keywords

diffusion processesreinforcement learningMDP (Markov decision process)

Mathematics Subject Classification ID

Optimal stochastic control (93E20) Stochastic learning and adaptive control (93E35) Diffusion processes (60J60) Markov and semi-Markov decision processes (90C40)

Related Items (2)

Continuity of cost in Borkar control topology and implications on discrete space and time approximations for controlled diffusions under several criteria ⋮ Approximate Q Learning for Controlled Diffusion Processes and Its Near Optimality

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Value iteration and adaptive dynamic programming for data-driven adaptive optimal control design
• Q-learning for continuous-time linear systems: A model-free infinite horizon optimal control approach
• Markov chains and stochastic stability
• Approximating value functions for controlled degenerate diffusion processes by using piece-wise constant policies.
• Asynchronous stochastic approximation and Q-learning
• On the rate of convergence of finite-difference approximations for Bellman's equations with variable coefficients
• \({\mathcal Q}\)-learning
• Neural networks-based backward scheme for fully nonlinear PDEs
• Improved order 1/4 convergence for piecewise constant policy approximation of stochastic control problems
• Nearly optimal control laws for nonlinear systems with saturating actuators using a neural network HJB approach
• Policy iterations for reinforcement learning problems in continuous time and space -- fundamental theory and methods
• Variational estimation of the drift for stochastic differential equations from the empirical density
• Algorithms for Reinforcement Learning
• On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
• An analysis of temporal-difference learning with function approximation
• On the convergence rate of approximation schemes for Hamilton-Jacobi-Bellman Equations
• Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction
• Error Bounds for Monotone Approximation Schemes for Hamilton--Jacobi--Bellman Equations
• Continuous‐time mean–variance portfolio selection: A reinforcement learning framework
• Approximate Q Learning for Controlled Diffusion Processes and Its Near Optimality

This page was built for publication: Approximate Q Learning for Controlled Diffusion Processes and Its Near Optimality