Learn More
F irst,w e c o nstru ct a statesp ac e inte rm s o f si ze, position, a nd o rie n ta tio n o f a b al l a nd a g oal i n a n i m age, and a n a cti on s p ac e i s d esi gne dinte rm s o f t h e a cti on c o m m ands tob ese n t t o t h e l e f t a nd r i g ht m oto rs of a m obi l e r o bot.T hi s c a uses a\state-a cti ondevi a tio n" p ro bl e m i n c o(More)
This paper presents a method of vision-based reinforcement learning by which a robot learns to shoot a ball into a goal, and discusses several issues in applying the reinforcement learning method to a real robot with vision sensor. First, a \state-action deviation" problem is found as a form of perceptual aliasing in constructing the state and action spaces(More)
We propose a method which acquires a purposive behavior for a mobile robot to shoot a ball into the goal by using a vision-based reinforcement learning. A mobile robot (an agent) does not need to know any parameters of the 3-D environment or its kinematic-s/dynamics. Information about the changes of the environment is only the image captured from a single(More)
A method is proposed which accomplishes a whole task consisting of plural subtasks by coordinating multiple behaviors acquired by a vision-based reinforcement learning. First, individual behaviors which achieve the corresponding subtasks are independently acquired by Q-learning, a widely used reinforcement learning method. Each learned behavior can be(More)
In [1], we have presented the soccer robot which had learned to shoot a ball into the goal using the Q-learning. In this paper, we discuss several issues in applying the Q-learning method to a real robot with vision sensor. First, to speed up the learning rate, we implement a mechanism of Learning form Easy Missions (or LEM) which is a similar technique to(More)
A method is proposed which acquires a purpo-sive behavior of shooting a ball into the goal avoiding collisions with an enemy. In [Asada et al., 1994], we have presented the soccer robot which learned to shoot a ball into the goal without any enemy, using the Q-learning, one of the reinforcement learning methods. Since a simple extension of the method is not(More)