Sciweavers

ATAL
2015
Springer

Learning Inter-Task Transferability in the Absence of Target Task Samples

8 years 6 months ago
Learning Inter-Task Transferability in the Absence of Target Task Samples
In a reinforcement learning setting, the goal of transfer learning is to improve performance on a target task by re-using knowledge from one or more source tasks. A key problem in transfer learning is how to choose appropriate source tasks for a given target task. Current approaches typically require that the agent has some experience in the target domain, or that the target task is specified by a model (e.g., a Markov Decision Process) with known parameters. To address these limitations, this paper proposes a framework for selecting source tasks in the absence of a known model or target task samples. Instead, our approach uses meta-data (e.g., attribute-value pairs) associated with each task to learn the expected benefit of transfer given a source-target task pair. To test the method, we conducted a large-scale experiment in the Ms. Pac-Man domain in which an agent played over 170 million games spanning 192 variations of the task. The agent used vast amounts of experience about tra...
Jivko Sinapov, Sanmit Narvekar, Matteo Leonetti, P
Added 16 Apr 2016
Updated 16 Apr 2016
Type Journal
Year 2015
Where ATAL
Authors Jivko Sinapov, Sanmit Narvekar, Matteo Leonetti, Peter Stone
Comments (0)