Evolving Neural Networks to Play Go

Authors:
Norman Richards;David E. Moriarty;Risto Miikkulainen
Affiliations:
The University of Texas at Austin, Austin, Tx 78712.;The University of Texas at Austin, Austin, Tx 78712.;The University of Texas at Austin, Austin, Tx 78712.
Venue:
Applied Intelligence
Year:
1998

Citing 6
Cited 13

The development of a world class Othello program

Artificial Intelligence - Special issue on computer chess
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Incremental evolution of complex general behavior

Adaptive Behavior - Special issue on environment structure and behavior
Evolving Obstacle Avoidance Behavior in a Robot Arm

Evolving Obstacle Avoidance Behavior in a Robot Arm
Symbiotic Evolution of Neural Networks in Sequential Decision Tasks

Symbiotic Evolution of Neural Networks in Sequential Decision Tasks
Forming neural networks through efficient and adaptive coevolution

Evolutionary Computation

Online Interactive Neuro-evolution

Neural Processing Letters
Book reviews

intelligence
Variable Hidden Layer Sizing in Elman Recurrent Neuro-Evolution

Applied Intelligence
Learning Time Allocation Using Neural Networks

CG '00 Revised Papers from the Second International Conference on Computers and Games
An empirical comparison of evolution and coevolution for designing artificial neural network game players

Proceedings of the 10th annual conference on Genetic and evolutionary computation
TOWARDS OPTIMIZING ENTERTAINMENT IN COMPUTER GAMES

Applied Artificial Intelligence
Fitness Diversity Parallel Evolution Algorithms in the Turtle Race Game

EvoWorkshops '09 Proceedings of the EvoWorkshops 2009 on Applications of Evolutionary Computing: EvoCOMNET, EvoENVIRONMENT, EvoFIN, EvoGAMES, EvoHOT, EvoIASP, EvoINTERACTION, EvoMUSART, EvoNUM, EvoSTOC, EvoTRANSLOG
In search of intelligent genes: the cartesian genetic programming computational neuron (CGPCN)

CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Scalable Neural Networks for Board Games

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
Introducing a round robin tournament into Blondie24

CIG'09 Proceedings of the 5th international conference on Computational Intelligence and Games
Resource awareness in computational intelligence

International Journal of Advanced Intelligence Paradigms
Adaptation of intelligent characters to changes of game environments

CIS'05 Proceedings of the 2005 international conference on Computational Intelligence and Security - Volume Part I
Immune based fuzzy agent plays checkers game

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Go is a difficult game for computers to master, and the best goprograms are still weaker than the average human player. Since thetraditional game playing techniques have proven inadequate, new approachesto computer go need to be studied. This paper presents a new approach tolearning to play go. The SANE (Symbiotic, Adaptive Neuro-Evolution) methodwas used to evolve networks capable of playing go on small boards with nopre-programmed go knowledge. On a 9 × 9 go board, networks that wereable to defeat a simple computer opponent were evolved within a few hundredgenerations. Most significantly, the networks exhibited several aspects ofgeneral go playing, which suggests the approach could scale up well.