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/}
}