Coordination Of Multiple Behaviors Acquired By A Vision-Based Reinforcement Learning (1994)
| Venue: | In Proc. of IEEE/RSJ/GI International Conference on Intelligent Robots and Systems 1994 (IROS '94 |
| Citations: | 24 - 4 self |
BibTeX
@INPROCEEDINGS{Asada94coordinationof,
author = {Minoru Asada and Eiji Uchibe and Shoichi Noda and Sukoya Tawaratsumida and Koh Hosoda},
title = {Coordination Of Multiple Behaviors Acquired By A Vision-Based Reinforcement Learning},
booktitle = {In Proc. of IEEE/RSJ/GI International Conference on Intelligent Robots and Systems 1994 (IROS '94},
year = {1994},
pages = {917--924}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
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 dierent action-value functions, switching action-value functions according to situations, and learning with previously obtained actionvalue 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 independe...
