Average Cost Optimal Control of Stochastic Systems Using Reinforcement Learning
Systems and Control
2020-10-14 v1 Machine Learning
Systems and Control
Optimization and Control
Abstract
This paper addresses the average cost minimization problem for discrete-time systems with multiplicative and additive noises via reinforcement learning. By using Q-function, we propose an online learning scheme to estimate the kernel matrix of Q-function and to update the control gain using the data along the system trajectories. The obtained control gain and kernel matrix are proved to converge to the optimal ones. To implement the proposed learning scheme, an online model-free reinforcement learning algorithm is given, where recursive least squares method is used to estimate the kernel matrix of Q-function. A numerical example is presented to illustrate the proposed approach.
Cite
@article{arxiv.2010.06236,
title = {Average Cost Optimal Control of Stochastic Systems Using Reinforcement Learning},
author = {Jing Lai and Junlin Xiong},
journal= {arXiv preprint arXiv:2010.06236},
year = {2020}
}
Comments
6 pages, 2 figures