UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Autonomous Transfer for Reinforcement Learning (2008)
Matthew E. Taylor
,
Gregory Kuhlmann
, and
Peter Stone
Recent work in transfer learning has succeeded in making reinforcement learning algorithms more efficient by incorporating knowledge from previous tasks. However, such methods typically must be provided either a full model of the tasks or an explicit relation mapping one task into the other. An autonomous agent may not have access to such high-level information, but would be able to analyze its experience to find similarities between tasks. In this paper we introduce Modeling Approximate State Transitions by Exploiting Regression (MASTER), a method for automatically learning a mapping from one task to another through an agent's experience. We empirically demonstrate that such learned relationships can significantly improve the speed of a reinforcement learning algorithm in a series of Mountain Car tasks. Additionally, we demonstrate that our method may also assist with the difficult problem of task selection for transfer.
View:
PDF
,
PS
,
HTML
Citation:
In
The Seventh International Joint Conference on Autonomous Agents and Multiagent Systems
, May 2008.
Bibtex:
@InProceedings{AAMAS08-taylor, title={Autonomous Transfer for Reinforcement Learning}, author={Matthew E. Taylor and Gregory Kuhlmann and Peter Stone}, booktitle={The Seventh International Joint Conference on Autonomous Agents and Multiagent Systems}, month={May}, url="http://www.cs.utexas.edu/users/ai-lab?AAMAS08-taylor", year={2008} }
People
Gregory Kuhlmann
Ph.D. Alumni
kuhlmann [at] cs utexas edu
Peter Stone
Faculty
pstone [at] cs utexas edu
Matthew Taylor
Ph.D. Alumni
taylorm [at] eecs wsu edu
Areas of Interest
Other Areas
Reinforcement Learning
Transfer Learning
Labs
Learning Agents