Foglino, F, Coletto Christakou, C and Leonetti, M orcid.org/0000-0002-3831-2400 (2019) An Optimization Framework for Task Sequencing in Curriculum Learning. In: 2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob). 2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), 19-22 Aug 2019, Oslo, Norway. IEEE , pp. 207-214. ISBN 978-1-5386-8128-2
Abstract
Curriculum learning in reinforcement learning is used to shape exploration by presenting the agent with increasingly complex tasks. The idea of curriculum learning has been largely applied in both animal training and pedagogy. In reinforcement learning, all previous task sequencing methods have shaped exploration with the objective of reducing the time to reach a given performance level. We propose novel uses of curriculum learning, which arise from choosing different objective functions. Furthermore, we define a general optimization framework for task sequencing and evaluate the performance of popular metaheuristic search methods on several tasks. We show that curriculum learning can be successfully used to: improve the initial performance, take fewer suboptimal actions during exploration, and discover better policies.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2019 IEEE. This is an author produced version of a paper published in 2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob). Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Uploaded in accordance with the publisher's self-archiving policy. |
Keywords: | Curriculum Learning; Transfer Learning; Reinforcement 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: | 13 Jun 2019 14:25 |
Last Modified: | 14 Nov 2019 17:34 |
Status: | Published |
Publisher: | IEEE |
Identification Number: | 10.1109/DEVLRN.2019.8850690 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:147033 |