Analysing Co-evolution Among Artificial 3D
Creatures
T. Miconi, и A. Channon. 7th International Conference and Evolution
Artificielle, EA 2005, том 3871 из Lecture Notes in Computer Science, стр. 167--178. Lille, France, Springer, (октября 2005)Revised Selected Papers.
DOI: doi:10.1007/11740698_15
Аннотация
This paper presents new accomplishments in the
coevolution of neurally controlled agents, and
introduces improved methods of coevolutionary analysis.
The experiments reported, on the coevolution of
physically simulated articulated creatures, are the
first to demonstrate realistic co-adapted behaviours
using general purpose neurons. The previous need for ad
hoc (problem-specific) neurons was a barrier to the
long-term evolution of new, emergent behaviours. Novel
behaviours are identified using an improved
coevolutionary analysis method that is both more
informative and an order of magnitude cheaper than the
original. Finally, individuals are cross-validated
between evolutionary runs, in an improved procedure for
evaluating global performance.
%0 Conference Paper
%1 DBLP:conf/ae/MiconiC05
%A Miconi, Thomas
%A Channon, Alastair
%B 7th International Conference and Evolution
Artificielle, EA 2005
%C Lille, France
%D 2005
%E Talbi, El-Ghazali
%E Liardet, Pierre
%E Collet, Pierre
%E Lutton, Evelyne
%E Schoenauer, Marc
%I Springer
%K algorithms, genetic programming
%P 167--178
%R doi:10.1007/11740698_15
%T Analysing Co-evolution Among Artificial 3D
Creatures
%U http://www.channon.net/alastair/papers/ea05.pdf
%V 3871
%X This paper presents new accomplishments in the
coevolution of neurally controlled agents, and
introduces improved methods of coevolutionary analysis.
The experiments reported, on the coevolution of
physically simulated articulated creatures, are the
first to demonstrate realistic co-adapted behaviours
using general purpose neurons. The previous need for ad
hoc (problem-specific) neurons was a barrier to the
long-term evolution of new, emergent behaviours. Novel
behaviours are identified using an improved
coevolutionary analysis method that is both more
informative and an order of magnitude cheaper than the
original. Finally, individuals are cross-validated
between evolutionary runs, in an improved procedure for
evaluating global performance.
%@ 3-540-33589-7
@inproceedings{DBLP:conf/ae/MiconiC05,
abstract = {This paper presents new accomplishments in the
coevolution of neurally controlled agents, and
introduces improved methods of coevolutionary analysis.
The experiments reported, on the coevolution of
physically simulated articulated creatures, are the
first to demonstrate realistic co-adapted behaviours
using general purpose neurons. The previous need for ad
hoc (problem-specific) neurons was a barrier to the
long-term evolution of new, emergent behaviours. Novel
behaviours are identified using an improved
coevolutionary analysis method that is both more
informative and an order of magnitude cheaper than the
original. Finally, individuals are cross-validated
between evolutionary runs, in an improved procedure for
evaluating global performance.},
added-at = {2008-06-19T17:46:40.000+0200},
address = {Lille, France},
author = {Miconi, Thomas and Channon, Alastair},
bibsource = {DBLP, http://dblp.uni-trier.de},
biburl = {https://www.bibsonomy.org/bibtex/2910ae5552bb30a91546146c601dcf009/brazovayeye},
booktitle = {7th International Conference and Evolution
Artificielle, EA 2005},
doi = {doi:10.1007/11740698_15},
editor = {Talbi, El-Ghazali and Liardet, Pierre and Collet, Pierre and Lutton, Evelyne and Schoenauer, Marc},
interhash = {819b6eb42aff7b6a1a2f874b58f8a6c0},
intrahash = {910ae5552bb30a91546146c601dcf009},
isbn = {3-540-33589-7},
keywords = {algorithms, genetic programming},
month = {October 26-28},
note = {Revised Selected Papers},
notes = {Published 2006},
pages = {167--178},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
timestamp = {2008-06-19T17:47:03.000+0200},
title = {Analysing Co-evolution Among Artificial 3{D}
Creatures},
url = {http://www.channon.net/alastair/papers/ea05.pdf},
volume = 3871,
year = 2005
}