Foglino, F, Coletto Christakou, C, Luna Gutierrez, R et al. (1 more author) (2019) Curriculum Learning for Cumulative Return Maximization. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence. International Joint Conference on Artificial Intelligence, 10-16 Aug 2019, Macao, China. IJCAI , pp. 2308-2314. ISBN 978-0-9992411-4-1
Abstract
Curriculum learning has been successfully used in reinforcement learning to accelerate the learning process, through knowledge transfer between tasks of increasing complexity. Critical tasks, in which suboptimal exploratory actions must be minimized, can benefit from curriculum learning, and its ability to shape exploration through transfer. We propose a task sequencing algorithm maximizing the cumulative return, that is, the return obtained by the agent across all the learning episodes. By maximizing the cumulative return, the agent not only aims at achieving high rewards as fast as possible, but also at doing so while limiting suboptimal actions. We experimentally compare our task sequencing algorithm to several popular metaheuristic algorithms for combinatorial optimization, and show that it achieves significantly better performance on the problem of cumulative return maximization. Furthermore, we validate our algorithm on a critical task, optimizing a home controller for a micro energy grid.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2019, International Joint Conferences on Artificial Intelligence. All rights reserved. No part of this book may be reproduced in any form by any electronic or mechanical means (including photocopying, recording, or information storage and retrieval) without permission in writing from the publisher. Reproduced in accordance with the publisher's self-archiving policy. |
Keywords: | Machine Learning: Reinforcement Learning; Machine Learning: Transfer, Adaptation, Multi-task Learning; Machine Learning: Developmental Learning; Machine Learning: Deep Learning |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Funding Information: | Funder Grant number EPSRC EP/R031193/1 |
Depositing User: | Symplectic Publications |
Date Deposited: | 12 Jun 2019 12:40 |
Last Modified: | 25 Sep 2019 09:38 |
Published Version: | https://www.ijcai19.org/ |
Status: | Published |
Publisher: | IJCAI |
Identification Number: | 10.24963/ijcai.2019/320 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:147036 |