Abstract
We introduce a kind of partial observability to the projective simulation (PS) learning method. It is done by adding a belief projection operator and an observability parameter to the original framework of the efficiency of the PS model. I provide theoretical formulations, network representations, and situated scenarios derived from the invasion toy problem as a starting point for some multi-agent PS models.
Abstract (translated by Google)
URL
http://arxiv.org/abs/1610.09372