HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Information Science and Technology / Faculty of Information Science and Technology >
Peer-reviewed Journal Articles, etc >

Establishing Interaction between Machine and Medaka using Deep Q-Network

This item is licensed under: Creative Commons Attribution 3.0 Unported

Files in This Item:
eai.3-12-2015.2262508-1.pdf380.57 kBPDFView/Open
Please use this identifier to cite or link to this item:http://hdl.handle.net/2115/64495

Title: Establishing Interaction between Machine and Medaka using Deep Q-Network
Authors: Nishimura, Ryo Browse this author
Hiroyuki, Iizuka Browse this author →KAKEN DB
Yamamoto, Masahito Browse this author →KAKEN DB
Keywords: machine animal interaction
deep Q network
real time
medaka
Issue Date: 27-Dec-2016
Publisher: ACM
Journal Title: EAI Endorsed Transactions on Creative Technologies
Volume: 16
Issue: 9
Publisher DOI: 10.4108/eai.3-12-2015.2262508
Abstract: Social interaction is the basic ability for animals to survive. It is difficult for a machine to interact with human or other animals because it is not clear how the machine should interact. This paper examines whether an artificial dot controlled by a machine can interact with a medaka and induce a desired behavior. The dot is displayed on a monitor. We use deep Q network (DQN) to learn how to move the dot. As a result, the DQN could learn some basic elements to interact with the medaka and the desired behavior could be induced.
Rights: Copyright © 2015 R. Nishimura et al., licensed to EAI. This is an open access article distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/3.0/), which permits unlimited use, distribution and reproduction in any medium so long as the original work is properly cited.
http://creativecommons.org/licenses/by/3.0/
Type: article
URI: http://hdl.handle.net/2115/64495
Appears in Collections:情報科学院・情報科学研究院 (Graduate School of Information Science and Technology / Faculty of Information Science and Technology) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

Submitter: 山本 雅人

Export metadata:

OAI-PMH ( junii2 , jpcoar )

MathJax is now OFF:


 

Feedback - Hokkaido University