Quantum Reinforcement Learning for Large-Scale Multi-Agent Decision-Making in Autonomous Aerial Networks

This paper addresses a new quantum computing-based multi-agent reinforcement learning (QMARL) algorithm which is inspired by the quantum neural network (QNN)-based centralized critic and multiple actor networks. The benefit of the proposed QMARL-based algorithm is in the action control dimension reduction where it can reduce the size into a logarithmic-scale when project value measure (PVM) is utilized. Therefore, our proposed QMARL-based algorithm is beneficial for massive-agent MARL training convergence. Moreover, the various applications of QMARL-based algorithms are presented in massive-scale unmanned aerial vehicle (UAV) networks. Lastly, our performance evaluation results verify that the proposed QMARL-based algorithm can successfully converge when massive-action dimensions should be utilized.