Fleet Control using Coregionalized Gaussian Process Policy Iteration

Research output: Chapter in Book/Report/Conference proceedingConference paperResearch

Abstract

In many settings, as for example wind farms, multiple machines are instantiated to perform the same task, which is called a fleet. The recent advances with respect to the Internet of Things allow control devices and/or machines to connect through cloud-based architectures in order to share information about their status and environment. Such an infrastructure allows seamless data sharing between fleet members, which could greatly improve the sample-efficiency of reinforcement learning techniques. However in practice, these machines, while almost identical in design, have small discrepancies due to production errors or degradation, preventing control algorithms to simply aggregate and employ all fleet data. We propose a novel reinforcement learning method that learns to transfer knowledge between similar fleet members and creates member-specific dynamical models for control. Our algorithm uses Gaussian processes to establish cross-member covariances. This is significantly different from standard transfer learning methods, as the focus is not on sharing information over tasks, but rather over system specifications. We demonstrate our approach on two benchmarks and a realistic wind farm setting. Our method significantly outperforms two baseline approaches, namely individual learning and joint learning where all samples are aggregated, in terms of the median and variance of the results.

Original languageEnglish
Title of host publicationProceedings of the 24th European Conference on Artificial Intelligence (ECAI 2020)
EditorsGiuseppe De Giacomo, Alejandro Catala, Bistra Dilkina, Michela Milano, Senen Barro, Alberto Bugarin, Jerome Lang
PublisherIOS Press
Pages1571-1578
Number of pages8
ISBN (Electronic)9781643681009
ISBN (Print)978-1-64368-100-9
DOIs
Publication statusPublished - 24 Aug 2020
EventEuropean Conference on Artificial Intelligence (ECAI 2020) - Santiago De Compostela, Spain
Duration: 29 Aug 20202 Sep 2020
Conference number: 24
http://ecai2020.eu/

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume325
ISSN (Print)0922-6389

Conference

ConferenceEuropean Conference on Artificial Intelligence (ECAI 2020)
Abbreviated titleECAI
CountrySpain
CitySantiago De Compostela
Period29/08/202/09/20
Internet address

Fingerprint Dive into the research topics of 'Fleet Control using Coregionalized Gaussian Process Policy Iteration'. Together they form a unique fingerprint.

Cite this