Title :
Use of the knowledge which is independence on reward in reinforcement learning
Author :
Miyazaki, Yoshiki ; Kurashige, Kentarou
Author_Institution :
Muroran Inst. of Technol., Univ. of Comput. Sci. & Syst. Eng., Muroran, Japan
Abstract :
Now, there are some techniques called machine learning, and reinforcement learning is one of the machine learning which often used for actual machine. In this study, we pay attention to the knowledge that does not depend on a reward in reinforcement learning, and we will improve learning efficiency by using it. Furthermore, we aim at letting agent coping with various tasks under environment where agent is put. In this paper, we propose the knowledge that does not depend on a reward, and we show utility by applying it to the problem that a task turns into under same environment.
Keywords :
control engineering computing; learning (artificial intelligence); robots; agent coping; machine learning; reinforcement learning; Computer errors; Computer science; Genetic algorithms; Humans; Learning systems; Machine learning; Neural networks; Robots; Supervised learning; Systems engineering and theory;
Conference_Titel :
Computational Intelligence in Robotics and Automation (CIRA), 2009 IEEE International Symposium on
Conference_Location :
Daejeon
Print_ISBN :
978-1-4244-4808-1
Electronic_ISBN :
978-1-4244-4809-8
DOI :
10.1109/CIRA.2009.5423225