Accelerating Reinforcement Learning through the Discovery of Useful Subgoals

Authors

Amy McGovern, University of Massachusetts - Amherst
Andrew G. Barto, University of Massachusetts - Amherst

Publication Date

2001

Abstract

An ability to adjust to changing environments and unforeseen circumstances is likely to be an important component of a successful autonomous space robot. This paper shows how to augment reinforcement learning algorithms with a method for automatically discovering certain types of subgoals online. By creating useful new subgoals while learning, the agent is able to accelerate learning on a current task and to transfer its expertise to related tasks through the reuse of its ability to attain subgoals. Subgoals are created based on commonalities across multiple paths to a solution. We cast the task of finding these commonalities as a multiple-instance learning problem and use the concept of diverse density to find solutions. We introduced this approach in [10] and here we present additional results for a simulated mobile robot task.

Comments

This paper was harvested from CiteSeer

Recommended Citation

McGovern, Amy and Barto, Andrew G., "Accelerating Reinforcement Learning through the Discovery of Useful Subgoals" (2001). Computer Science Department Faculty Publication Series. 12.
Retrieved from https://scholarworks.umass.edu/cs_faculty_pubs/12