DocumentCode :
1712514
Title :
Propagating learned behaviors from a virtual agent to a physical robot in reinforcement learning
Author :
Yamaguchi, Tomohiro ; Masubuchi, Motohmi ; Tanaka, Yasuhiro ; Yachida, Masahiko
Author_Institution :
Dept. of Syst. Eng., Osaka Univ., Japan
fYear :
1996
Firstpage :
855
Lastpage :
859
Abstract :
For a physical robot to acquire behaviors, it is important for it to learn in the physical environment. Since reinforcement learning requires large computation costs as well as a lot of time in the physical environment, most research has performed learning by simulation. However, this does not work well in the real world. Realizing reinforcement learning of a physical robot in a physical environment requires both an adaptation for the diversity of possible situations and a high-speed learning method that can learn from fewer trials. This paper describes cooperative reinforcement learning based on propagating the learned behaviors of a virtual agent to a physical robot in order to accelerate learning in a physical environment. The method consists of two parts: (1) preparation learning in a virtual environment to accelerate initial learning, which accounts for most of the learning cost; and, (2) refinement learning in a physical environment by using the virtual learning results as an initial behavior set of a physical robot. Experimental results are given for a ball-pushing task with the physical robot and a virtual agent
Keywords :
knowledge based systems; learning (artificial intelligence); robot programming; robots; software agents; ball-pushing task; cooperative reinforcement learning; high-speed learning method; learned behaviors; physical robot; virtual agent; virtual environment; Accelerated aging; Acceleration; Computational efficiency; Computational modeling; Intelligent robots; Learning systems; Physics computing; Steel; Systems engineering and theory; Virtual environment;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Evolutionary Computation, 1996., Proceedings of IEEE International Conference on
Conference_Location :
Nagoya
Print_ISBN :
0-7803-2902-3
Type :
conf
DOI :
10.1109/ICEC.1996.542714
Filename :
542714
Link To Document :
بازگشت