UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
IFSA: Incremental Feature-Set Augmentation for Reinforcement Learning Tasks (2007)
Mazda Ahmadi
,
Matthew E. Taylor
, and
Peter Stone
Reinforcement learning is a popular and successful framework for many agent-related problems because only limited environmental feedback is necessary for learning. While many algorithms exist to learn effective policies in such problems, learning is often used to solve real world problems, which typically have large state spaces, and therefore suffer from the ``curse of dimensionality.'' One effective method for speeding-up reinforcement learning algorithms is to leverage expert knowledge. In this paper, we propose a method for dynamically augmenting the agent's feature set in order to speed up value-function-based reinforcement learning. The domain expert divides the feature set into a series of subsets such that a novel problem concept can be learned from each successive subset. Domain knowledge is also used to order the feature subsets in order of their importance for learning. Our algorithm uses the ordered feature subsets to learn tasks significantly faster than if the entire feature set is used from the start. Incremental Feature-Set Augmentation (IFSA) is fully implemented and tested in three different domains: Gridworld, Blackjack and RoboCup Soccer Keepaway. All experiments show that IFSA can significantly speed up learning and motivates the applicability of this novel RL method.
View:
PDF
,
PS
,
HTML
Citation:
In
The Sixth International Joint Conference on Autonomous Agents and Multiagent Systems
, May 2007.
Bibtex:
@InProceedings{AAMAS07-ahmadi, title={IFSA: Incremental Feature-Set Augmentation for Reinforcement Learning Tasks}, author={Mazda Ahmadi and Matthew E. Taylor and Peter Stone}, booktitle={The Sixth International Joint Conference on Autonomous Agents and Multiagent Systems}, month={May}, url="http://www.cs.utexas.edu/users/ai-lab?AAMAS07-ahmadi", year={2007} }
People
Mazda Ahmadi
Formerly affiliated Ph.D. Student
mazda [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
Labs
Learning Agents