Shoichi Noda

Learn More
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,(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)
This paper proposes an ecient method of robot learning by which a set of pairs of a state and an action are constructed to achieve a goal. Basic ideas of our method are as follows: i) Since autonomous construction of state and action spaces is generally a very dicult problem, we construct a state space so that a group of situations in which an action(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)
Robot learning such as reinforcement learning generally needs a well-dened state space in order to converge. However, to build such a state space is one of the main issues of the robot learning because of the interdependence between state and action spaces, which resembles to the well known \chicken and egg" problem. This paper proposes two methods of(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)