Co-Evolving a Go-Playing Neural network

Alex Lubberts; Risto Miikkulainen

Co-Evolving a Go-Playing Neural network

Alex Lubberts, Risto Miikkulainen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Professional

2 Downloads (Pure)

Abstract

When evolving a game-playing neural network, fitness is usually measured by playing against existing opponents. In this article that need is overcome by applying the competitive co-evolutionary techniques of competitive fitness sharing, shared sampling, and hall of fame to the SANE neuro-evolution method.

Original language	English
Title of host publication	Coevolution: Turning Adaptive Algorithms upon Themselves
Subtitle of host publication	Birds-of-a-Feather Workshop Genetic and Evolutionary Computation Conference
Place of Publication	San Francisco, CA, USA
Number of pages	6
Publication status	Published - 3 Jul 2001
Event	Genetic and Evolutionary Computation Conference GECCO 2001 - San Francisco, United States Duration: 3 Jul 2001 → 13 Jul 2001

Conference

Conference	Genetic and Evolutionary Computation Conference GECCO 2001
Abbreviated title	GECCO 2001
Country/Territory	United States
City	San Francisco
Period	3/07/01 → 13/07/01
Other	A recombination of the Sixth Annual Genetic Programming Conference (GP-2001) and the International Conference on Genetic Algorithms (ICGA-2001)

Access to Document

Lubberts2001co-evolvingFinal published version, 194 KB

Cite this

@inproceedings{49d86f3d9c0046e498af233c0dd1349c,

title = "Co-Evolving a Go-Playing Neural network",

abstract = "When evolving a game-playing neural network, fitness is usually measured by playing against existing opponents. In this article that need is overcome by applying the competitive co-evolutionary techniques of competitive fitness sharing, shared sampling, and hall of fame to the SANE neuro-evolution method.",

author = "Alex Lubberts and Risto Miikkulainen",

year = "2001",

month = jul,

day = "3",

language = "English",

booktitle = "Coevolution: Turning Adaptive Algorithms upon Themselves",

note = "Genetic and Evolutionary Computation Conference GECCO 2001, GECCO 2001 ; Conference date: 03-07-2001 Through 13-07-2001",

}

TY - GEN

T1 - Co-Evolving a Go-Playing Neural network

AU - Lubberts, Alex

AU - Miikkulainen, Risto

PY - 2001/7/3

Y1 - 2001/7/3

N2 - When evolving a game-playing neural network, fitness is usually measured by playing against existing opponents. In this article that need is overcome by applying the competitive co-evolutionary techniques of competitive fitness sharing, shared sampling, and hall of fame to the SANE neuro-evolution method.

AB - When evolving a game-playing neural network, fitness is usually measured by playing against existing opponents. In this article that need is overcome by applying the competitive co-evolutionary techniques of competitive fitness sharing, shared sampling, and hall of fame to the SANE neuro-evolution method.

M3 - Conference contribution

BT - Coevolution: Turning Adaptive Algorithms upon Themselves

CY - San Francisco, CA, USA

T2 - Genetic and Evolutionary Computation Conference GECCO 2001

Y2 - 3 July 2001 through 13 July 2001

ER -

Co-Evolving a Go-Playing Neural network

Abstract

Conference

Access to Document

Fingerprint

Cite this