Developing neural structure of two agents that play checkers using cartesian genetic programming

A developmental model of neural network is presented and evaluated in the game of Checkers. The network is developed using cartesian genetic programs (CGP) as genotypes. Two agents are provided with this network and allowed to co-evolve untill they start playing better. The network that occurs by running theses genetic programs has a highly dynamic morphology in which neurons grow, and die, and neurite branches together with synaptic connections form and change in response to situations encountered on the checkers board. The method has no board evaluation function, no explicit learning rules and no human expertise at playing checkers is used. The results show that, after a number of generations, by playing each other the agents begin to play much better and can easily beat agents that occur in earlier generations. Such learning abilities are encoded at a genetic level rather than at the phenotype level of neural connections. Categories and Subject Descriptors I.2.2 [ARTIFICIAL INTELLI...

• Type: Conference
• Year: 2008
• Where: GECCO
• Authors: Gul Muhammad Khan, Julian Francis Miller, David M. Halliday
• Keywords: Cartesian Genetic Programs, GECCO 2008, Genetic Programs, Neural Networks, Optimization