Transactions of the Institute of Systems, Control and Information Engineers
Online ISSN : 2185-811X
Print ISSN : 1342-5668
ISSN-L : 1342-5668
Papers
Knowledge Selection based on Value in Transfer Learning
Naoki Kotani
Author information
JOURNALS FREE ACCESS

2015 Volume 28 Issue 6 Pages 275-283

Details
Abstract

This paper is aimed at reducing the amount of knowledge to avoid lower learning performance of an agent in transfer learning. In transfer or multitask reinforcement learning problems, the agent reuses policies which were learned in past tasks in order to efficiently solve unknown tasks. Therefore,the agent has a large number of state-action pairs as knowledge. But, at the same time, it causes both explosively increasing the amount of knowledge and decreasing the learning speed. This paper proposes a method for reducing the amount of knowledge on the basis of value. The effectiveness of the proposed method was verified with the simulation of the reaching problem for a multi-link robot arm. The proposed method achieves a reduction of the amount of knowledge and learning time. It also improves learning performance of the agent.

Information related to the author
© 2015 The Institute of Systems, Control and Information Engineers
Previous article Next article
feedback
Top