Future University Hakodate Academic Archive >
研究者 >
情報アーキテクチャ学科 >
ピトヨ・ハルトノ >

このアイテムの引用には次の識別子を使用してください: http://hdl.handle.net/10445/5286

タイトル: Fast reinforcement learning for simple physical robots
著者: Hartono, Pitoyo
Kakita, Sachiko
アブストラクト: In the past few years, the field of autonomous robot has been rigorously studied and non-industrial applications of robotics are rapidly emerging. One of the most interesting aspects of this field is the development of the learning ability which enables robots to autonomously adapt to given environments without human guidance. As opposed to the conventional methods of robots' control, where human logically design the behavior of a robot, the ability to acquire action strategies through some learning processes will not only significantly reduce the production costs of robots but also improves the applicability of robots in wider tasks and environments. However, learning algorithms usually require large calculation cost, which make them unsuitable for robots with limited resources. In this study, we propose a simple two-layered neural network that implements a novel and fast Reinforcement Learning. The proposed learning method requires significantly less calculation resources, hence applicable to small physical robots running in the real world environments.For this study, we built several simple robots and implemented the proposed learning mechanism to them. In the experiments, to evaluate the efficacy of the proposed learning mechanism, several robots were simultaneously trained to acquire obstacle avoidance strategies in a same environment, thus, forming a dynamic environment where the learning task is substantially harder than in the case of learning in a static environment.
研究業績種別: 原著論文/Original Paper
資料種別: Journal Article
査読有無: あり/yes
単著共著: 共著/joint
発表雑誌名,発表学会名など: Memetic Computing Journal
巻: 1
号: 4
開始ページ: 305
終了ページ: 313
年月日: 2009年
出版社: Springer





Powered by DSpace Software Copyright © 2002-2007 MIT and Hewlett-Packard