Title :
Coordination of multiple behaviors acquired by a vision-based reinforcement learning
Author :
Asada, Minoru ; Uchibe, Eiji ; Noda, Shoichi ; Tawaratsumida, Sukoya ; Hosoda, Koh
Author_Institution :
Dept. of Mech. Eng. for Comput.-Controlled Machinery, Osaka Univ., Japan
Abstract :
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 represented by an action-value function in terms of state of the environment and robot action. Next, three kinds of coordinations of multiple behaviors are considered; simple summation of different action-value functions, switching action-value functions according to situations, and learning with previously obtained action-value functions as initial values of a new action-value function. A task of shooting a ball into the goal avoiding collisions with an enemy is examined. The task can be decomposed into a ball shooting subtask and a collision avoiding subtask. These subtasks should be accomplished simultaneously, but they are not independent of each other
Keywords :
intelligent control; learning (artificial intelligence); mobile robots; object recognition; robot vision; Q-learning; action-value function; ball shooting task; collision avoidance; mobile robots; multiple behaviors coordination; robot action; vision-based reinforcement learning; Autonomous agents; Computer simulation; Convergence; Learning automata; Machinery; Robot kinematics; Robot sensing systems; Robotics and automation;
Conference_Titel :
Intelligent Robots and Systems '94. 'Advanced Robotic Systems and the Real World', IROS '94. Proceedings of the IEEE/RSJ/GI International Conference on
Print_ISBN :
0-7803-1933-8
DOI :
10.1109/IROS.1994.407484