On Learning Robot Behaviors.
Minoru Asada · TRANSACTIONS OF THE JAPAN SOCIETY OF MECHANICAL ENGINEERS Series C · 1996
Reinforcement learning has recently been receiving increased attention as a method for robot learning with little or no a priori knowledge and higher capability of reactive and adaptive behaviors. This paper presents a framework of the reinforcement learning, and several issues in applying the method to real robot tasks. Then, examples of real robot applications, especially vision-based reinforcement learning methods are intorduced to show how they cope with these issues.