On Reward Distribution in Reinforcement Learning of Multi-Agent Surveillance Systems With Temporal Logic Specifications

In multi-agent systems, it is important to design a reward based on the contribution of each agent for efficient learning. In this paper, we propose a reward distribution method for a surveillance system based on our previously proposed multi-agent reinforcement learning method with an aggregator, in which a control specification is described by a linear temporal logic formula. In this method, the aggregator computes and distributes rewards according to the actions that agents take on the surveillance system. Finally, the performance is shown by a numerical simulation of a surveillance problem as an example.