Links

Sample-efficiency is crucial in reinforcement learning tasks, especially when a large number of similar yet distinct tasks have to be learned. For example, consider a smart wheelchair learning to exit many differently-furnished offices on a building floor. Sequentially learning each of these tasks from scratch would be highly inefficient. A step towards a satisfying solution is the use of transfer learning: exploiting the knowledge acquired in previous (or source) tasks to tackle new (or target) tasks. Existing work mainly focuses on exploiting only one source policy as an advisor for the fresh agent, even when there are several expert source policies available. However, using only one advisor requires artificial mechanisms to limit its influence in areas where the source task and the target task differ, in order for the advisee not to be misled. In this paper, we present a novel approach to transfer learning in which all available source policies are exploited to help learn several related new tasks. Moreover, our approach is compatible with tasks that differ by their transition functions, which is rarely considered in the transfer reinforcement learning literature. Our in-depth empirical evaluation demonstrates that our approach significantly improves sample-efficiency.
Original languageEnglish
Title of host publicationProceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019)
PublisherCEUR Workshop Proceedings
Number of pages16
Volume2491
Publication statusPublished - 6 Nov 2019
Event31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on Machine Learning, BNAIC/BENELEARN 2019 - Brussels, Belgium
Duration: 6 Nov 20198 Nov 2019

Publication series

NameCEUR Workshop Proceedings
PublisherCEUR-WS.org
Number11
Volume2491
ISSN (Electronic)1613-0073

Conference

Conference31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on Machine Learning, BNAIC/BENELEARN 2019
CountryBelgium
CityBrussels
Period6/11/198/11/19

ID: 49510154