Evolution of Neural Controllers with Adaptive Synapses and Compact Genetic Encoding

Abstract. This paper is concerned with arti cial evolution of neurocontrollers with adaptive synapses for autonomous mobile robots. The method consists of encoding on the genotype a set of local modi cation rules that synapses obey while the robot freely moves in the environment 2]. The synaptic weights are not encoded on the genotype. In the experiments presented here, a \behavior-based tness" function gives reproductive advantage to robots that can solve a sequential task. The results show that evolutionary adaptive controllers solve the task much faster and better than evolutionary standard (non-adaptive) controllers, that the method scales up well to large architectures whereas standard controllers do not, and that evolved adaptive controllers are not trivial and cannot be reduced to a xed-weight network. 1 Evolution and Learning Arti cial evolution of adaptive individuals can providecomputational advantages and richer adaptive dynamics 1] with respect to evolution of individu...

• Type: Conference
• Year: 1999
• Where: ECAL
• Authors: Dario Floreano, Joseba Urzelai
• Keywords: Adaptive Controllers, Arti Cial Evolution, Artificial Intelligence, ECAL 1999, Evolutionary Adaptive Controllers