A Projective Simulation Scheme for Partially-Observable Multi-Agent Systems
arXiv:1610.09372 · doi:10.1007/s42484-021-00037-x
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.
28 pages, 21 figures