neural networks research group
areas
people
projects
demos
publications
software/data
Source Task Creation for Curriculum Learning (2016)
Sanmit Narvekar
and
Jivko Sinapov
and
Matteo Leonetti
and
Peter Stone
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.
View:
PDF
,
HTML
Citation:
In
Proceedings of the 15th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2016)
, Singapore, May 2016.
Bibtex:
@inproceedings{AAMAS16-Narvekar, title={Source Task Creation for Curriculum Learning}, author={Sanmit Narvekar and Jivko Sinapov and Matteo Leonetti and Peter Stone}, booktitle={Proceedings of the 15th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2016)}, month={May}, address={Singapore}, url="http://nn.cs.utexas.edu/?narvekar:aamas16", year={2016} }
Presentation:
Slides (PDF)
People
Matteo Leonetti
matteo [at] cs utexas edu
Sanmit Narvekar
sanmit [at] cs utexas edu
Jivko Sinapov
jsinapov [at] cs utexas edu
Peter Stone
pstone [at] cs utexas edu
Areas of Interest
Transfer Learning
Reinforcement Learning