@inproceedings{290c9e5e7400484da10906f0385b2b16,
title = "Empirical Dynamic Programming for Controlled Diffusion Processes",
abstract = "We consider Markov chain approximation for optimal control of diffusion processes under infinite horizon discounted cost optimality and apply the simulation-based Empirical Value Iteration to estimate the value function of each approximating chain. We follow a nested multi-grid discretization of the state space to establish weak convergence of the value function sequence to the value function of the original controlled diffusion. We illustrate the convergence performance of the model on the popular Benes' bang-bang control problem [Bene{\v s} (1974)].",
keywords = "Diffusion processes, Markov decision process, Numerical methods for optimal control, Reinforcement learning, Stochastic optimal control, Value iteration",
author = "Karumanchi, {Sambhu H.} and Belabbas, {Mohamed A.} and Naira Hovakimyan",
note = "This work has been supported by the National Science Foundation (CMMI-2135925). The authors would like to thank Prof Vivek Borkar for his valuable suggestions.; 22nd IFAC World Congress ; Conference date: 09-07-2023 Through 14-07-2023",
year = "2023",
month = jul,
day = "1",
doi = "10.1016/j.ifacol.2023.10.854",
language = "English (US)",
series = "IFAC-PapersOnLine",
publisher = "Elsevier B.V.",
number = "2",
pages = "11235--11241",
editor = "Hideaki Ishii and Yoshio Ebihara and Jun-ichi Imura and Masaki Yamakita",
booktitle = "IFAC-PapersOnLine",
edition = "2",
}