Name
Title | ||
|---|---|---|
Approximate dynamic programming using fluid and diffusion approximations with applications to power management |
Abstract | ||
|---|---|---|
TD learning and its refinements are powerful tools for approximating the solution to dynamic programming problems. However, the 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 for TD learning based on choosing the function class using the solutions to associated fluid and diffusion approximations. In order to illustrate this new approach, the paper focuses on an application to dynamic speed scaling for power management. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/CDC.2009.5399685 | Shanghai |
Keywords | DocType | Volume |
approximate dynamic programming,power management,nonlinear control,approximation theory,td learning,learning systems,optimal stochastic control,finite-dimensional function class,dynamic programming problems,adaptive control,dynamic speed scaling.,dynamic speed scaling,diffusion approximation,multidimensional systems,dynamic programming,machine learning,fluid approximation,markov processes,generators,cost function,mathematical model | Conference | abs/1307.1759 |
ISSN | ISBN | Citations |
0191-2216 E-ISBN : 978-1-4244-3872-3 | 978-1-4244-3872-3 | 7 |
PageRank | References | Authors |
0.61 | 15 | 8 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wei Chen | 1 | 7 | 0.61 |
| Dayu Huang | 2 | 48 | 7.81 |
| Ankur A. Kulkarni | 3 | 106 | 20.95 |
| Jayakrishnan Unnikrishnan | 4 | 280 | 21.34 |
| Zhu Quanyan | 5 | 1295 | 116.31 |
| Prashant G. Mehta | 6 | 414 | 52.29 |
| Sean P. Meyn | 7 | 603 | 75.28 |
| Adam Wierman | 8 | 1635 | 106.57 |