Foglino, F, Leonetti, M orcid.org/0000-0002-3831-2400, Sagratella, S et al. (1 more author) (2019) A Gray-Box Approach for Curriculum Learning. In: Le Thi, H, Le, H and Pham Dinh, T, (eds.) Advances in Intelligent Systems and Computing. 6th World Congress on Global Optimization (WGCO 2019): Optimization of Complex Systems: Theory, Models, Algorithms and Applications, 08-10 Jul 2019, Metz, France. Springer Verlag , pp. 720-729. ISBN 9783030218027
Abstract
Curriculum learning is often employed in deep reinforcement learning to let the agent progress more quickly towards better behaviors. Numerical methods for curriculum learning in the literature provides only initial heuristic solutions, with little to no guarantee on their quality. We define a new gray-box function that, including a suitable scheduling problem, can be effectively used to reformulate the curriculum learning problem. We propose different efficient numerical methods to address this gray-box reformulation. Preliminary numerical results on a benchmark task in the curriculum learning literature show the viability of the proposed approach.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Copyright, Publisher and Additional Information: | © 2020, Springer Nature Switzerland AG. This is a post-peer-review, pre-copyedit version of a conference paper published in Advances in Intelligent Systems and Computing. The final authenticated version is available online at: http://doi.org/10.1007/978-3-030-21803-4_72. |
Keywords: | Curriculum learning; Reinforcement learning; Black-box optimization; Scheduling problem |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 26 Jul 2019 11:24 |
Last Modified: | 15 Jun 2020 00:40 |
Status: | Published |
Publisher: | Springer Verlag |
Identification Number: | 10.1007/978-3-030-21803-4_72 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:149047 |