Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks

Details Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks

2011-06-09

arxiv.org/abs/1106.1796v1

Journal Of Artificial Intelligence Research, Volume 16, pages 59-104, 2002

Computer Science

Artificial Intelligence

Scientific paper

10.1613/jair.904

This paper discusses a system that accelerates reinforcement learning by using transfer from related tasks. Without such transfer, even if two tasks are very similar at some abstract level, an extensive re-learning effort is required. The system achieves much of its power by transferring parts of previously learned solutions rather than a single complete solution. The system exploits strong features in the multi-dimensional function produced by reinforcement learning in solving a particular task. These features are stable and easy to recognize early in the learning process. They generate a partitioning of the state space and thus the function. The partition is represented as a graph. This is used to index and compose functions stored in a case base to form a close approximation to the solution of the new task. Experiments demonstrate that function composition often produces more than an order of magnitude increase in learning rate compared to a basic reinforcement learning algorithm.

Affiliated with

Also associated with

No associations

Rating

Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-580250