We explore using particle swarm optimization on problems with noisy performance evaluation, focusing on unsupervised robotic learning. We adapt a technique of overcoming noise used in genetic algorithms for use with particle swarm optimization, and evaluate the performance of both the original algorithmand the noise-resistantmethod for several numerical problems with added noise, as well as unsupervised learning of obstacle avoidance using one or more robots.
Alcherio Martinoli, Cyrill Silvan Baumann
Olga Fink, Vinay Sharma, Manav Manav
Silvestro Micera, Simone Romeni, Elena Losanno, Luca Pierantoni