Saved in:
Bibliographic Details
Main Authors: Hasan, Cengis, Agapitos, Alexandros, Lynch, David, Castagna, Alberto, Cruciata, Giorgio, Wang, Hao, Milenovic, Aleksandar
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.19462
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929331696041984
author Hasan, Cengis
Agapitos, Alexandros
Lynch, David
Castagna, Alberto
Cruciata, Giorgio
Wang, Hao
Milenovic, Aleksandar
author_facet Hasan, Cengis
Agapitos, Alexandros
Lynch, David
Castagna, Alberto
Cruciata, Giorgio
Wang, Hao
Milenovic, Aleksandar
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_19462
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Continual Model-based Reinforcement Learning for Data Efficient Wireless Network Optimisation
Hasan, Cengis
Agapitos, Alexandros
Lynch, David
Castagna, Alberto
Cruciata, Giorgio
Wang, Hao
Milenovic, Aleksandar
Machine Learning
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.
title Continual Model-based Reinforcement Learning for Data Efficient Wireless Network Optimisation
topic Machine Learning
url https://arxiv.org/abs/2404.19462