UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Co-Evolving A Go-Playing Neural Network (2001)
Alex Lubberts
and
Risto Miikkulainen
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. This approach is tested by evolving networks to play go on small boards. Networks evolved through co-evolution were compared against those evolved against the gnugo program. The co-evolutionary techniques were found to speed up the evolution and to result in better networks not limited by the quality of the opponent.
View:
PDF
,
PS
Citation:
In
Coevolution: {T}urning Adaptive Algorithms Upon Themselves, Birds-of-a-Feather Workshop, Genetic and Evolutionary Computation Conference ({GECCO}-2001)
, pp. 6 2001.
Bibtex:
@InProceedings{lubberts:geccoworkshop01, title={Co-Evolving A Go-Playing Neural Network}, author={Alex Lubberts and Risto Miikkulainen}, booktitle={Coevolution: {T}urning Adaptive Algorithms Upon Themselves, Birds-of-a-Feather Workshop, Genetic and Evolutionary Computation Conference ({GECCO}-2001)}, pages={6}, url="http://www.cs.utexas.edu/users/ai-lab?lubberts:geccows01", year={2001} }
People
Alex Lubberts
Formerly affiliated Visitor
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Areas of Interest
Applications
Evolutionary Computation
Game Playing
Neuroevolution
Reinforcement Learning
Labs
Neural Networks