An unsupervised learning of a layered network and its application to a motion acquisition
Ikuko Nishikawa, Kohei Matsunaga · 2003
An unsupervised learning for a layered network is applied to a motion acquisition of an autonomous agent. A basic algorithm is extended in the following two ways for temporal series learning. One is a temporal reward assignment, and the other is a network with temporal integration units. Several simulations show a successful learning of collision avoidance and a capture of both static and moving targets.