Continual Model-Based Reinforcement Learning for Data Efficient Wireless Network Optimisation
Abstract
We present a method that addresses the pain point of long lead-time required to deploy cell-level parameter optimisation policies to new wireless network sites. Given a sequence of action spaces represented by overlapping subsets of cell-level configuration parameters provided by domain experts, we formulate throughput optimisation as Continual Reinforcement Learning of control policies. Simulation results suggest that the proposed system is able to shorten the end-to-end deployment lead-time by two-fold compared to a reinitialise-and-retrain baseline without any drop in optimisation gain.
Cite
Text
Hasan et al. "Continual Model-Based Reinforcement Learning for Data Efficient Wireless Network Optimisation." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2023. doi:10.1007/978-3-031-43427-3_18Markdown
[Hasan et al. "Continual Model-Based Reinforcement Learning for Data Efficient Wireless Network Optimisation." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2023.](https://mlanthology.org/ecmlpkdd/2023/hasan2023ecmlpkdd-continual/) doi:10.1007/978-3-031-43427-3_18BibTeX
@inproceedings{hasan2023ecmlpkdd-continual,
title = {{Continual Model-Based Reinforcement Learning for Data Efficient Wireless Network Optimisation}},
author = {Hasan, Cengis and Agapitos, Alexandros and Lynch, David and Castagna, Alberto and Cruciata, Giorgio and Wang, Hao and Milenovic, Aleksandar},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2023},
pages = {295-311},
doi = {10.1007/978-3-031-43427-3_18},
url = {https://mlanthology.org/ecmlpkdd/2023/hasan2023ecmlpkdd-continual/}
}