Svetlik, M, Leonetti, M orcid.org/0000-0002-3831-2400, Sinapov, J et al. (3 more authors) (2017) Automatic Curriculum Graph Generation for Reinforcement Learning Agents. In: Markovitch, S and Singh, S, (eds.) Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17). AAAI-17, 04-09 Feb 2017, San Francisco, USA. Association for the Advancement of Artificial Intelligence , pp. 2590-2596. ISBN 978-1-57735-782-7
Abstract
In recent years, research has shown that transfer learning methods can be leveraged to construct curricula that sequence a series of simpler tasks such that performance on a final target task is improved. A major limitation of existing approaches is that such curricula are handcrafted by humans that are typically domain experts. To address this limitation, we introduce a method to generate a curriculum based on task descriptors and a novel metric of transfer potential. Our method automatically generates a curriculum as a directed acyclic graph (as opposed to a linear sequence as done in existing work). Experiments in both discrete and continuous domains show that our method produces curricula that improve the agent’s learning performance when compared to the baseline condition of learning on the target task from scratch.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Keywords: | curriculum learning; reinforcement learning; transfer learning; machine learning; |
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: | 06 Dec 2016 17:20 |
Last Modified: | 16 Nov 2017 12:22 |
Published Version: | https://aaai.org/ocs/index.php/AAAI/AAAI17/paper/v... |
Status: | Published |
Publisher: | Association for the Advancement of Artificial Intelligence |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:108931 |