Approximate dynamic programming using fluid and diffusion approximations with applications to power management
Machine Learning
2016-04-18 v2 Optimization and Control
Abstract
Neuro-dynamic programming is a class of powerful techniques for approximating the solution to dynamic programming equations. In their most computationally attractive formulations, these techniques provide the approximate solution only within a prescribed finite-dimensional function class. Thus, the question that always arises is how should the function class be chosen? The goal of this paper is to propose an approach using the solutions to associated fluid and diffusion approximations. In order to illustrate this approach, the paper focuses on an application to dynamic speed scaling for power management in computer processors.
Cite
@article{arxiv.1307.1759,
title = {Approximate dynamic programming using fluid and diffusion approximations with applications to power management},
author = {Wei Chen and Dayu Huang and Ankur A. Kulkarni and Jayakrishnan Unnikrishnan and Quanyan Zhu and Prashant Mehta and Sean Meyn and Adam Wierman},
journal= {arXiv preprint arXiv:1307.1759},
year = {2016}
}
Comments
Submitted to SIAM Journal on Control and Optimization (SICON), July 2013