Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


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

Jivko Sinapov, Sanmit Narvekar, Matteo Leonetti, and Peter Stone. Learning Inter-Task Transferability in the Absence of Target Task Samples. In Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2015.

Download

[PDF]337.2kB  

Abstract

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 transfer learning in the domain to model the benefit (or detriment) of transferring knowledge from one task to another. Subsequently, the agent successfully selected appropriate source tasks for previously unseen target tasks.

BibTeX Entry

@InProceedings{AAMAS15-sinapov,
  title={Learning Inter-Task Transferability in the Absence of Target
  Task Samples},
  author={Jivko Sinapov and Sanmit Narvekar and Matteo Leonetti and Peter Stone},
  booktitle={Proceedings of the International Conference on Autonomous
  Agents and Multiagent Systems (AAMAS)},
  year={2015},
  organization={ACM},
  abstract={
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 transfer learning in the domain to model the benefit (or detriment) of transferring knowledge from one task to another. Subsequently, the agent successfully selected appropriate source tasks for previously unseen target tasks.
  },
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed Nov 25, 2020 21:31:00