Reinforcement Learning that Emerges Teamwork in Heterogeneous Multi-Agent Environments
Yuki Hyodo, Takuto Sakuma, Shōhei Kato · 2021 IEEE 10th Global Conference on Consumer Electronics (GCCE) · 2021
This paper approaches problem-solving in multi-agent environments using deep reinforcement learning. In this paper, we solve a cooperative air rescue task by a fixed-wing aircraft and a helicopter as a problem in multi-agent environments. They have different abilities about speed and expected tasks. Therefore, the purpose of this research is to emerge teamwork that takes advantage of different abilities in multi-agent environments. This paper proposes a method for agents to learn to communicate. We compare among the "Proposed model," "No comm," "MADDPG" using an air rescue task. From two experiments, we confirm the accomplishment of the cooperative task by the proposed method and the effectiveness of the proposed method.