Evolutionary Construction of a Simulator for Real
Robots
S. Kamio, and H. Iba. Proceedings of the 2004 IEEE Congress on Evolutionary
Computation, page 2202--2209. Portland, Oregon, IEEE Press, (20-23 June 2004)
Abstract
In order to acquire useful motions of a real-world
robot, it is necessary to carry out learning in a real
environment. However, learning is difficult within a
real environment. In addition, the acceleration of
learning is required for a practical execution. In this
paper, we propose an approach to the learning
acceleration using data retrieved from the real
environment. This consists of the method of
automatically constructing the simulator from real data
and of learning a robot controller with the simulator.
The experimental results suggest that our GP-based
technique enables the effective controller learning.
%0 Conference Paper
%1 kamio:2004:ecoasfrr
%A Kamio, Shotaro
%A Iba, Hitoshi
%B Proceedings of the 2004 IEEE Congress on Evolutionary
Computation
%C Portland, Oregon
%D 2004
%I IEEE Press
%K Evolutionary agents algorithms, genetic intelligent programming,
%P 2202--2209
%T Evolutionary Construction of a Simulator for Real
Robots
%U http://www.iba.k.u-tokyo.ac.jp/papers/2004/kamioCEC2004.pdf
%X In order to acquire useful motions of a real-world
robot, it is necessary to carry out learning in a real
environment. However, learning is difficult within a
real environment. In addition, the acceleration of
learning is required for a practical execution. In this
paper, we propose an approach to the learning
acceleration using data retrieved from the real
environment. This consists of the method of
automatically constructing the simulator from real data
and of learning a robot controller with the simulator.
The experimental results suggest that our GP-based
technique enables the effective controller learning.
%@ 0-7803-8515-2
@inproceedings{kamio:2004:ecoasfrr,
abstract = {In order to acquire useful motions of a real-world
robot, it is necessary to carry out learning in a real
environment. However, learning is difficult within a
real environment. In addition, the acceleration of
learning is required for a practical execution. In this
paper, we propose an approach to the learning
acceleration using data retrieved from the real
environment. This consists of the method of
automatically constructing the simulator from real data
and of learning a robot controller with the simulator.
The experimental results suggest that our GP-based
technique enables the effective controller learning.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {Portland, Oregon},
author = {Kamio, Shotaro and Iba, Hitoshi},
biburl = {https://www.bibsonomy.org/bibtex/224686cf17019a34c1cd658ac501257db/brazovayeye},
booktitle = {Proceedings of the 2004 IEEE Congress on Evolutionary
Computation},
interhash = {e02a5b553b06f2c78dd39058d51ec00e},
intrahash = {24686cf17019a34c1cd658ac501257db},
isbn = {0-7803-8515-2},
keywords = {Evolutionary agents algorithms, genetic intelligent programming,},
month = {20-23 June},
notes = {CEC 2004 - A joint meeting of the IEEE, the EPS, and
the IEE.},
pages = {2202--2209},
publisher = {IEEE Press},
timestamp = {2008-06-19T17:42:51.000+0200},
title = {Evolutionary Construction of a Simulator for Real
Robots},
url = {http://www.iba.k.u-tokyo.ac.jp/papers/2004/kamioCEC2004.pdf},
year = 2004
}