Reinforcement Learning for Dynamic Channel Allocation in Cellular Telephone Systems
Cached
Download Links
| Citations: | 111 - 5 self |
BibTeX
@MISC{Singh_reinforcementlearning,
author = {Satinder Singh and Dimitri Bertsekas},
title = {Reinforcement Learning for Dynamic Channel Allocation in Cellular Telephone Systems},
year = {}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
In cellular telephone systems, an important problem is to dynamically allocate the communication resource (channels) so as to maximize service in a stochastic caller environment. This problem is naturally formulated as a dynamic programming problem and we use a reinforcement learning (RL) method to find dynamic channel allocation policies that are better than previous heuristic solutions. The policies obtained perform well for a broad variety of call traffic patterns. We present results on a large cellular system with approximately 49^49 states.
Citations
| 1060 | Learning to predict by the methods of temporal differences - Sutton - 1988 |
| 554 | Nonlinear Programming. Athena Scientific - Bertsekas - 1995 |
| 472 | Learning to act using real-time dynamic programming - Barto, Bradtke, et al. - 1995 |
| 334 | Practical issues in temporal difference learning - Tesauro - 1992 |
| 250 | Improving elevator performance using reinforcement learning - Crites, Barto - 1996 |
| 147 | Learning to predict by the methods of temporal di erence - Sutton - 1988 |
| 61 | Comparisons of channel assignment strategies in cellular mobile telephone systems - Zhang, Yum - 1989 |
| 59 | Practical issues in temporal dierences learning - Tesauro - 1992 |
| 13 | Performance Limits for Channelized Cellular Telephone Systems - McEliece, Sivarajan - 1994 |
| 12 | A Dynamic Channel Allocation Technique Based on Hopfield Neural Networks - Re, Fantacci, et al. - 1996 |
| 6 | Dynamic Programming and Optimal Control: Vols 1 and 2 - Bertsekas |
| 3 | Dynamic Programming and Optimal Control, Vols 1 and 2. Athena Scienti c - Bertsekas - 1995 |
