A Game Theory-Reinforcement Learning Approach to Cooperation for UAVs

To execute a variety of collaborative tasks, the cooperation for unmanned aerial vehicles (UAVs) with complicated interactions under dynamic environments is a challenging and critical issue. This paper studies the cooperation issue for UAVs under dynamic environments through an approach of game theory-reinforcement learning (GT-RL) approach, which combines the advantages of both game theory and reinforcement learning. First, to cope with the complicated interactions of UAVs, the cluster of UAVs is modeled as a public goods game with asymmetrical environmental feedback. Then, reinforcement learning is adopted to optimize decision-making of UAVs under unknown and dynamic environments through comparing the dynamic behaviors of UAVs, where a novel dynamics system offers a more comprehensive understanding on cooperative behavior among UAVs. Finally, the simulation results show that the GT-RL approach can effectively promote cooperation among UAVs in completing the collaborative tasks.