ACCNet: Actor-Coordinator-Critic Net for "Learning-to-Communicate" with Deep Multi-agent Reinforcement Learning
Abstract
Communication is a critical factor for the big multi-agent world to stay organized and productive. Typically, most previous multi-agent "learning-to-communicate" studies try to predefine the communication protocols or use technologies such as tabular reinforcement learning and evolutionary algorithm, which can not generalize to changing environment or large collection of agents. In this paper, we propose an Actor-Coordinator-Critic Net (ACCNet) framework for solving "learning-to-communicate" problem. The ACCNet naturally combines the powerful actor-critic reinforcement learning technology with deep learning technology. It can efficiently learn the communication protocols even from scratch under partially observable environment. We demonstrate that the ACCNet can achieve better results than several baselines under both continuous and discrete action space environments. We also analyse the learned protocols and discuss some design considerations.
Cite
@article{arxiv.1706.03235,
title = {ACCNet: Actor-Coordinator-Critic Net for "Learning-to-Communicate" with Deep Multi-agent Reinforcement Learning},
author = {Hangyu Mao and Zhibo Gong and Yan Ni and Zhen Xiao},
journal= {arXiv preprint arXiv:1706.03235},
year = {2017}
}
Comments
V3 of original submission. Actor-Critic Method for Multi-agent Learning-to-Communicate based on Deep Reinforcement Learning, It is suitable for both continuous and discrete action space environments