Reinforcement Learning for Dynamic Channel Allocation in Cellular Telephone Systems
Abstract
In cellular telephone systems, an important problem is to dynami(cid:173) cally allocate the communication resource (channels) so as to max(cid:173) imize 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 traf(cid:173) fic patterns. We present results on a large cellular system with approximately 4949 states.
Cite
Text
Singh and Bertsekas. "Reinforcement Learning for Dynamic Channel Allocation in Cellular Telephone Systems." Neural Information Processing Systems, 1996.Markdown
[Singh and Bertsekas. "Reinforcement Learning for Dynamic Channel Allocation in Cellular Telephone Systems." Neural Information Processing Systems, 1996.](https://mlanthology.org/neurips/1996/singh1996neurips-reinforcement/)BibTeX
@inproceedings{singh1996neurips-reinforcement,
title = {{Reinforcement Learning for Dynamic Channel Allocation in Cellular Telephone Systems}},
author = {Singh, Satinder P. and Bertsekas, Dimitri P.},
booktitle = {Neural Information Processing Systems},
year = {1996},
pages = {974-980},
url = {https://mlanthology.org/neurips/1996/singh1996neurips-reinforcement/}
}