A robot behavior-learning experiment using Particle Swarm Optimization for training a neural-based animat

— We investigate the use of Particle Swarm Optimization (PSO), and compare with Genetic Algorithms (GA), for a particular robot behavior-learning task: the training of an animat behavior totally determined by a fully-recurrent neural network, and with which we try to fulfill a simple exploration and food foraging task. The target behavior is simple, but the learning task is challenging because of the dynamic complexity of fully-recurrent neural networks. We show that standard PSO yield very good results for this learning problem, and appears to be much more effective than simple GA. Keywords— animat, behavior-learning, genetic algorithms, particle swarm optimization, recurrent neural network.

• Type: Conference
• Year: 2008
• Where: ICARCV
• Authors: Fabien Moutarde
• Keywords: Fully-recurrent Neural Networks, ICARCV 2008, Neural Network, Particle Swarm Optimization, Robotics