IEEJ Transactions on Electronics, Information and Systems
Online ISSN : 1348-8155
Print ISSN : 0385-4221
ISSN-L : 0385-4221
<Softcomputing, Learning>
A Rationally Oriented Forgettable Profit Sharing
Sadamori KoujakuKota WatanabeHajime Igarashi
Author information
JOURNAL FREE ACCESS

2012 Volume 132 Issue 3 Pages 448-454

Details
Abstract
In this paper, Rationally oriented Forgettable Profit Sharing method (RFPS) for reinforcement learning is proposed. Although the Profit Sharing (PS) provides good performances in real environments, its learning is often slow in long term tasks because it is difficult to determine the adequate discount rate which satisfies the Miyazaki rational theorem. There are several rationality-relaxed PS methods which work well for such tasks. However, these PS may result in many irrational loops. The proposed method fulfills the rationality by forgetting the reinforced irrational loops. This method can be easily combined with ordinary PS methods and performs well in long term tasks. The simulation results show that the proposed method can learn more efficiently than the conventional PS methods.
Content from these authors
© 2012 by the Institute of Electrical Engineers of Japan
Previous article Next article
feedback
Top