Co-Evolving a Go-Playing Neural network

Alex Lubberts, Risto Miikkulainen

Research output: Chapter in Book/Report/Conference proceedingConference contributionProfessional

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 languageEnglish
Title of host publicationCoevolution: Turning Adaptive Algorithms upon Themselves
Subtitle of host publicationBirds-of-a-Feather Workshop Genetic and Evolutionary Computation Conference
Place of PublicationSan Francisco, CA, USA
Number of pages6
Publication statusPublished - 3 Jul 2001
EventGenetic and Evolutionary Computation Conference GECCO 2001 - San Francisco, United States
Duration: 3 Jul 200113 Jul 2001

Conference

ConferenceGenetic and Evolutionary Computation Conference GECCO 2001
Abbreviated titleGECCO 2001
CountryUnited States
CitySan Francisco
Period3/07/0113/07/01
OtherA recombination of the Sixth Annual Genetic Programming Conference (GP-2001) and the International Conference on Genetic Algorithms (ICGA-2001)

Fingerprint Dive into the research topics of 'Co-Evolving a Go-Playing Neural network'. Together they form a unique fingerprint.

Cite this