A Projective Simulation Scheme for Partially-Observable Multi-Agent Systems
This work addresses partially-observable environments for multi-agent systems, though it appears incremental as it builds directly on existing projective simulation methods.
The authors extended projective simulation learning to partially-observable multi-agent systems by adding a belief projection operator and observability parameter, providing theoretical formulations, network representations, and invasion toy problem scenarios.
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.