neural networks research group
areas
people
projects
demos
publications
software/data
Evolving Neural Networks To Play Go (1998)
Norman Richards
,
David Moriarty
, and
Risto Miikkulainen
Go is a difficult game for computers to master, and the best go programs are still weaker than the average human player. Since the traditional game playing techniques have proven inadequate, new approaches to computer go need to be studied. This paper presents a new approach to learning to play go. The SANE (Symbiotic, Adaptive Neuro-Evolution) method was used to evolve networks capable of playing go on small boards with no pre-programmed go knowledge. On a 9 X 9 go board, networks that were able to defeat a simple computer opponent were evolved within a few hundred generations. Most significantly, the networks exhibited several aspects of general go playing, which suggests the approach could scale up well.
View:
PDF
,
PS
Citation:
In Thomas B{"a}ck, editors,
Proceedings of the Seventh International Conference on Genetic Algorithms (ICGA-97, East Lansing, MI)
, 768-775, 1998. San Francisco, CA: Morgan Kaufmann.
Bibtex:
@InProceedings{richards:icga97, title={Evolving Neural Networks To Play Go}, author={Norman Richards and David Moriarty and Risto Miikkulainen}, booktitle={Proceedings of the Seventh International Conference on Genetic Algorithms (ICGA-97, East Lansing, MI)}, journal={Applied Intelligence}, editor={Thomas B{"a}ck}, publisher={San Francisco, CA: Morgan Kaufmann}, pages={768-775}, url="http://nn.cs.utexas.edu/?richards:apin98", year={1998} }
People
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
David E. Moriarty
Ph.D. Alumni
moriarty [at] alumni utexas net
Norman Richards
Undergraduate Alumni
orb [at] toki dhs org
Areas of Interest
Evolutionary Computation
Neuroevolution
Reinforcement Learning
Game Playing
Applications