期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 -, 期 -, 页码 -出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2023.3309608
关键词
Large-scale multiagent; neighboring communication; reinforcement learning (RL); variational information flow
In this work, a novel method called neighboring variational information flow (NVIF) is proposed to enhance communication among neighboring agents and address the limitations of existing methods in large-scale multiagent systems. A two-stage training mechanism is introduced to stabilize the training process, and theoretical analysis and experiment results demonstrate the superiority and potential of the proposed method.
Communication-based multiagent reinforcement learning (MARL) has shown promising results in promoting cooperation by enabling agents to exchange information. However, the existing methods have limitations in large-scale multiagent systems due to high information redundancy, and they tend to overlook the unstable training process caused by the online-trained communication protocol. In this work, we propose a novel method called neighboring variational information flow (NVIF), which enhances communication among neighboring agents by providing them with the maximum information set (MIS) containing more information than the existing methods. NVIF compresses the MIS into a compact latent state while adopting neighboring communication. To stabilize the overall training process, we introduce a two-stage training mechanism. We first pretrain the NVIF module using a randomly sampled offline dataset to create a task-agnostic and stable communication protocol, and then use the pretrained protocol to perform online policy training with RL algorithms. Our theoretical analysis indicates that NVIF-proximal policy optimization (PPO), which combines NVIF with PPO, has the potential to promote cooperation with agent-specific rewards. Experiment results demonstrate the superiority of our method in both heterogeneous and homogeneous settings. Additional experiment results also demonstrate the potential of our method for multitask learning.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据