UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Behavior Transfer for Value-Function-Based Reinforcement Learning (2005)
Matthew E. Taylor
and
Peter Stone
Temporal difference (TD) learning methods have become popular reinforcement learning techniques in recent years. TD methods have had some experimental successes and have been shown to exhibit some desirable properties in theory, but have often been found very slow in practice. A key feature of TD methods is that they represent policies in terms of value functions. In this paper we introduce emphbehavior transfer, a novel approach to speeding up TD learning by transferring the learned value function from one task to a second related task. We present experimental results showing that autonomous learners are able to learn one multiagent task and then use behavior transfer to markedly reduce the total training time for a more complex task.
View:
PDF
,
PS
,
HTML
Citation:
In
The Fourth International Joint Conference on Autonomous Agents and Multiagent Systems
, Frank Dignum and Virginia Dignum and Sven Koenig and Sarit Kraus and Munindar P. Singh and Michael Wooldridge (Eds.), pp. 53-59, New York, NY, July 2005. ACM Press.
Bibtex:
@InProceedings{AAMAS05-transfer, title={Behavior Transfer for Value-Function-Based Reinforcement Learning}, author={Matthew E. Taylor and Peter Stone}, booktitle={The Fourth International Joint Conference on Autonomous Agents and Multiagent Systems}, month={July}, editor={Frank Dignum and Virginia Dignum and Sven Koenig and Sarit Kraus and Munindar P. Singh and Michael Wooldridge}, address={New York, NY}, publisher={ACM Press}, pages={53-59}, url="http://www.cs.utexas.edu/users/ai-lab?AAMAS05-transfer", year={2005} }
People
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