A Deep Reinforcement Learning Method based on Deterministic Policy Gradient for Multi-Agent Cooperative Competition

Deep reinforcement learning in multi-agent scenario is important for real-world applications but presents challenges beyond those seen in single agent settings. This paper proposes a method to train a team of multiple types of agents to cooperate against another team of agents. Furthermore, this paper studies how to train multiple types of agents to collaborate better on their team tasks, and analyses the influence of various factors on agents' policy. In the computer experiments, agents are divided into attacking agents and defending agents. The results show that attacking agents which play the roles of deceivers can attract most of defending agents and help the other attacking agents to reach their targets successfully. Choosing appropriate length of training could help agents learn better action policy. The experiments results reveal that the number of agents has an effect on the performance of our proposed method. Increasing the number of deceivers in attacking agents can significantly increase the mission success of attacking team, but the computational complexity will rise and more episodes are needed to train agents.