Machine Learning

, Volume 23, Issue 2, pp 279–303

Purposive Behavior Acquisition for a Real Robot by Vision-Based Reinforcement Learning

  • Minoru Asada
  • Shoichi Noda
  • Sukoya Tawaratsumida
  • Koh Hosoda
Article

DOI: 10.1023/A:1018237008823

Cite this article as:
Asada, M., Noda, S., Tawaratsumida, S. et al. Machine Learning (1996) 23: 279. doi:10.1023/A:1018237008823

Abstract

This paper presents a method of vision-based reinforcement learning by which a robot learns to shoot a ball into a goal. We discuss several issues in applying the reinforcement learning method to a real robot with vision sensor by which the robot can obtain information about the changes in an environment. First, we construct a state space in terms of size, position, and orientation of a ball and a goal in an image, and an action space is designed in terms of the action commands to be sent to the left and right motors of a mobile robot. This causes a state-action deviation problem in constructing the state and action spaces that reflect the outputs from physical sensors and actuators, respectively. To deal with this issue, an action set is constructed in a way that one action consists of a series of the same action primitive which is successively executed until the current state changes. Next, to speed up the learning time, a mechanism of Learning from Easy Missions (or LEM) is implemented. LEM reduces the learning time from exponential to almost linear order in the size of the state space. The results of computer simulations and real robot experiments are given.

reinforcement learning vision learning from easy mission state-action deviation 
Download to read the full article text

Copyright information

© Kluwer Academic Publishers 1996

Authors and Affiliations

  • Minoru Asada
    • 1
  • Shoichi Noda
    • 1
  • Sukoya Tawaratsumida
    • 1
  • Koh Hosoda
    • 1
  1. 1.Dept. of Mech. Eng. for Computer-Controlled Machinery Osaka UniversityOsaka 565Japan

Personalised recommendations