An Approach to the Piano Mover's Problem Using Hierarchic Reinforcement Learning

Yuko ISHIWAKA  Tomohiro YOSHIDA  Hiroshi YOKOI  Yukinori KAKAZU  

IEICE TRANSACTIONS on Information and Systems   Vol.E87-D   No.8   pp.2106-2113
Publication Date: 2004/08/01
Online ISSN: 
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Distributed Cooperation and Agents
reinforcement learning,  piano mover's problem,  heterogeneous multi-agent,  find-path problem,  obstacle avoidance,  

Full Text: PDF(1.7MB)>>
Buy this Article

We attempt to achieve corporative behavior of autonomous decentralized agents constructed via Q-Learning, which is a type of reinforcement learning. As such, in the present paper, we examine the piano mover's problem including a find-path problem. We propose a multi-agent architecture that has an external agent and internal agents. Internal agents are homogenous and can communicate with each other. The movement of the external agent depends on the composition of the actions of the internal agents. By learning how to move through the internal agents, avoidance of obstacles by the object is expected. We simulate the proposed method in a two-dimensional continuous world. Results obtained in the present investigation reveal the effectiveness of the proposed method.