Narvekar, S, Peng, B, Leonetti, M orcid.org/0000-0002-3831-2400 et al. (3 more authors) (2020) Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey. Journal of Machine Learning Research, 21. 181. ISSN 1532-4435
Abstract
Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks in which the agent has only limited environmental feedback. Despite many advances over the past three decades, learning in many domains still requires a large amount of interaction with the environment, which can be prohibitively expensive in realistic scenarios. To address this problem, transfer learning has been applied to reinforcement learning such that experience gained in one task can be leveraged when starting to learn the next, harder task. More recently, several lines of research have explored how tasks, or data samples themselves, can be sequenced into a curriculum for the purpose of learning a problem that may otherwise be too difficult to learn from scratch. In this article, we present a framework for curriculum learning (CL) in reinforcement learning, and use it to survey and classify existing CL methods in terms of their assumptions, capabilities, and goals. Finally, we use our framework to find open problems and suggest directions for future RL curriculum learning research.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2020 Sanmit Narvekar, Bei Peng, Matteo Leonetti, Jivko Sinapov, Matthew E. Taylor, and Peter Stone. This is an open access article under the terms of the Creative Commons Attribution License (CC-BY). |
Keywords: | curriculum learning; reinforcement learning; transfer 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: | 21 May 2021 09:03 |
Last Modified: | 21 May 2021 09:03 |
Published Version: | https://jmlr.org/papers/v21/ |
Status: | Published |
Publisher: | Journal of Machine Learning Research |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:174122 |