2021/09/05 by Zhenhui Ye, Ye, Zhenhui, Xiaohong Jiang +5 · 1 citation
Computer Science · Physics and Astronomy · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Complex Network Analysis Techniques #Computer science #FOS: Computer and information sciences #Graph #Machine Learning (cs.LG) #Multiagent Systems (cs.MA) #Observable #Physics #Reinforcement Learning in Robotics #Theoretical computer science #cs.AI #cs.LG #cs.MA
paper · pdf · doi:10.48550/arxiv.2109.02032
published in arXiv (Cornell University) (Cornell University) · 9 pages, 6 figures, 1 table. Under review
arxiv created 2021/09/05 · openalex publication_date 2021/09/05 · arxiv updated 2021/09/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The recent progress in multi-agent deep reinforcement learning(MADRL) makes it more practical in real-world tasks, but its relatively poor scalability and the partially observable constraints raise challenges to its performance and deployment. Based on our intuitive observation that the human society could be regarded as a large-scale partially observable environment, where each individual has the function of communicating with neighbors and remembering its own experience, we propose a novel network structure called hierarchical graph recurrent network(HGRN) for multi-agent cooperation under partial observability. Specifically, we construct the multi-agent system as a graph, use the hierarchical graph attention network(HGAT) to achieve communication between neighboring agents, and exploit GRU to enable agents to record historical information. To encourage exploration and improve robustness, we design a maximum-entropy learning method to learn stochastic policies of a configurable target action entropy. Based on the above technologies, we proposed a value-based MADRL algorithm called Soft-HGRN and its actor-critic variant named SAC-HRGN. Experimental results based on three homogeneous tasks and one heterogeneous environment not only show that our approach achieves clear improvements compared with four baselines, but also demonstrates the interpretability, scalability, and transferability of the proposed model. Ablation studies prove the function and necessity of each component.