Narvekar, S, Sinapov, J, Leonetti, M orcid.org/0000-0002-3831-2400 et al. (1 more author) (2016) Source Task Creation for Curriculum Learning. In: Proceedings of the 15th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2016). International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 09-13 May 2016, Singapore. ACM ISBN 978-1-4503-4239-1
Abstract
Transfer learning in reinforcement learning has been an active area of research over the past decade. In transfer learning, training on a source task is leveraged to speed up or otherwise improve learning on a target task. This paper presents the more ambitious problem of curriculum learning in reinforcement learning, in which the goal is to design a sequence of source tasks for an agent to train on, such that final performance or learning speed is improved. We take the position that each stage of such a curriculum should be tailored to the current ability of the agent in order to promote learning new behaviors. Thus, as a first step towards creating a curriculum, the trainer must be able to create novel, agent-specific source tasks. We explore how such a space of useful tasks can be created using a parameterized model of the domain and observed trajectories on the target task. We experimentally show that these methods can be used to form components of a curriculum and that such a curriculum can be used successfully for transfer learning in 2 challenging multiagent reinforcement learning domains.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) > Artificial Intelligence & Biological Systems (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 15 Nov 2016 12:23 |
Last Modified: | 15 Nov 2016 23:42 |
Published Version: | http://www.ifaamas.org/Proceedings/aamas2016/forms... |
Status: | Published |
Publisher: | ACM |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:97772 |