Self-Partitioning State Space for Behavior Acquisition of Vision-Based Mobile Robots
Takayuki Nakamura and Tsukasa Ogasawara
Nara Institute of Science and Technology, Graduate School of Information Sciences, Takayama-cho 8916-5, Ikoma, Nara 630-0101, Japan
An input generalization problem is one of the most important in applying reinforcement learning to real robot tasks. To cope with this problem, we propose a self-partitioning state space algorithm, which can make nonuniform quantization of state space. To show that our algorithm has generalization capability, we apply our method to two tasks in which a soccer robot shoots a ball into a goal and prevent a ball from entering a goal. To show the validity of this method, the experimental results for computer simulation and a real robot are shown.
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.
Copyright© 2001 by Fuji Technology Press Ltd. and Japan Society of Mechanical Engineers. All right reserved.