AbstractSwarm Multi-Agent Logistics Competition Entry: QPlus

The AbstractSwarm Framework [1] was developed to study multi-agent simulation for optimizing logistics scenarios, with a special focus on (but not restricted to) hospital logistics. The basics of a solution to the accompanying competition [2] and the included benchmark problems is to be presented in this paper. To achieve this, Q-Learning [5, 7, 8] is used to determine scores for possible actions an agent can take depending on the state of the AbstractSwarm Graph representing the environment. Every action receives multiple such scores which are in turn aggregated, hence the name "QPlus".