Proceedings of the Annual Conference of the Institute of Systems, Control and Information Engineers
The 54th Annual Conference of the Institute of Systems, Control and Information Engineers
Session ID : F342
Conference information

Learning Data Correction for EDA-RL
*Hisashi HandaTokue Nishimura
Author information
CONFERENCE PROCEEDINGS FREE ACCESS

Details
Abstract
Estimation of Distribution Algorithms for Reinforcement Learning Problems, proposed by us, are a novel approach for realizing autonomous learning agents. In this study, we proposed a learning data correction mechanism for acceralating learning speed. The mechanism firstly detect redundant sequences of state-action pairs, then remove them. Several experimental results show the effectiveness of the proposed method.
Content from these authors
© 2010 The Institute of Systems, Control and Information Engineers
Previous article Next article
feedback
Top