A Graph-Based PPO Approach in Multi-UAV Navigation for Communication Coverage

Multi-Agent Reinforcement Learning (MARL) is widely used to solve various problems in real life. In the multi-agent reinforcement learning tasks, there are multiple agents in the environment, the existing Proximal Policy Optimization (PPO) algorithm can be applied to multi-agent rein-forcement learning. However, it cannot deal with the communication problem between agents. In order to resolve this issue, we propose a Graph-based PPO algorithm, this approach can solve the communication problem between agents and it can enhance the exploration efficiency of agents in the environment and speed up the learning process. We apply our algorithms to the task of multi-UAV navigation for communication coverage to verify the functionality and performance of our proposed algorithms.

Automated summary

Multi-Agent Reinforcement Learning (MARL) is widely used to solve real-life problems. Existing algorithms cannot handle the communication problem between agents. We propose a Graph-based PPO algorithm to address this issue, which improves exploration efficiency and learning speed. We apply this algorithm to multi-UAV communication coverage task for verification.