Accelerating Reinforcement Learning through the Discovery of Useful Subgoals
This paper was harvested from CiteSeer
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  and here we present additional results for a simulated mobile robot task.
Amy McGovern and Andrew G. Barto. "Accelerating Reinforcement Learning through the Discovery of Useful Subgoals" 2001
Available at: http://works.bepress.com/andrew_barto/8