An Approach to the Piano Mover's Problem Using Hierarchic Reinforcement Learning(Distributed Cooperation and Agents)
スポンサーリンク
概要
- 論文の詳細を見る
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 multiagent 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.
- 社団法人電子情報通信学会の論文
- 2004-08-01
著者
-
Yoshida Tomohiro
Exploratory Research Ii Drug Discovery Laboratories Yoshitomi Pharmaceutical Industries Ltd.
-
Yokoi Hiroshi
Faculty Of Complex Systems Engineering Hokkaido University
-
Kakazu Y
Faculty Of Complex Systems Engineering Hokkaido University
-
Kakazu Yukinori
Faculty Of Engineering Hokkaido University
-
ISHIWAKA Yuko
Hakodate Institute of National College of Technology
-
YOSHIDA Tomohiro
Hakodate Institute of National College of Technology
-
Yoshida T
Hakodate Institute Of National College Of Technology
-
KAKAZU Yukinori
Faculty of Complex Systems Engineering, Hokkaido University
関連論文
- Preparation and Pharmacological Evaluation of Novel Glycoprotein (Gp) IIb/IIIa Antagonists. 2. Condensed Heterocyclic Derivatives
- Preparation and Pharmacological Evaluation of Novel Glycoprotein (Gp) IIb/IIIa Antagonists. 1. The Selection of Naphthalene Derivatives
- Tool Failure Detecting by ID3
- An Approach to the Piano Mover's Problem Using Hierarchic Reinforcement Learning(Distributed Cooperation and Agents)
- The effect of Pitch Accenting om Japanese Text-to-Speech Understanding(Cyber Net Robot 2,Session: TP1-D)
- Using Electromyogram to Analyze Skill Acquiring Patterns in Reaching Tasks(Sensing and Data Fusion,Session: MA1-A)
- Framework of Information Processing Using the Vibrating Potential Field : Theories and Applications
- A Study on a Logistic CIM Simulator -Tuning Weights for a Warehouse Stock Assignment Problem-
- Local Modification of a Free-Formed Surface While Preserving Shape Date
- Self-Organization In Morphogenesis of Cellular Slime Molds using concentration gradient of cAMP(Bio-inspired Robot,Session: TP2-C)