Graphcomm: A Graph Neural Network Based Method for Multi-Agent Reinforcement Learning
Siqi Shen, Yongquan Fu, Huayou Su, Hengyue Pan, Peng Qiao, Yong Dou, Cheng Wang
Abstract
The communication among agents is important for Multi-Agent Reinforcement Learning (MARL). In this work, we propose GraphComm, a method makes use of the relation-ships among agents for MARL communication. GraphComm takes the explicit relations (e.g., agent types), which can be provided through some knowledge background, into account to better model the relationships among agents. Besides explicit relations, GraphComm considers implicit relations, which are formed by agent interactions. GraphComm use Graph Neural Networks (GNNs) to model the relational information, and use GNNs to assist the learning of agent communication. We show that GraphComm can obtain better results than state-of-the-art methods on the challenging StarCraft II unit micromanagement tasks through extensive experimental evaluation.
BibTeX
@inproceedings{icassp2021_graphcommagraphn,
title = {Graphcomm: A Graph Neural Network Based Method for Multi-Agent Reinforcement Learning},
author = {Siqi Shen and Yongquan Fu and Huayou Su and Hengyue Pan and Peng Qiao and Yong Dou and Cheng Wang},
booktitle = {ICASSP 2021},
year = {2021}
}