Efficient Policy Generation in Multi-Agent Systems via Hypergraph Neural Network

2022-03-07 · Bin Zhang, Yunpeng Bai, Zhiwei Xu, Dapeng Li, Guoliang Fan

The application of deep reinforcement learning in multi-agent systems introduces extra challenges. In a scenario with numerous agents, one of the most important concerns currently being addressed is how to develop sufficient collaboration between diverse agents. To address this problem, we consider the form of agent interaction based on neighborhood and propose a multi-agent reinforcement learning (MARL) algorithm based on the actor-critic method, which can adaptively construct the hypergraph structure representing the agent interaction and further implement effective information extraction and representation learning through hypergraph convolution networks, leading to effective cooperation. Based on different hypergraph generation methods, we present two variants: Actor Hypergraph Convolutional Critic Network (HGAC) and Actor Attention Hypergraph Critic Network (ATT-HGAC). Experiments with different settings demonstrate the advantages of our approach over other existing methods.

📄 PDF Abstract BibTeX arXiv:2203.03265

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingDeep Reinforcement LearningMulti-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Representation Learning

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

HyperGraphPro: Progress-Aware Reinforcement Learning for Structure-Guided Hypergraph RAG

2026-01-25 · Jinyoung Park, Sanghyeok Lee, Omar Zia Khan, Hyunwoo J. Kim 외 arxiv

Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a promising paradigm that organizes external knowledge into structured graphs of entities and relations, enabling large language models (LLMs) to perform com…

Multi-hop Question Answering Reinforcement Learning Semantic Similarity Knowledge Graphs

Hypergraphon Mean Field Games

2022-03-30 · Kai Cui, Wasiur R. KhudaBukhsh, Heinz Koeppl

We propose an approach to modelling large-scale multi-agent dynamical systems allowing interactions among more than just pairs of agents using the theory of mean field games and the notion of hypergraphons, which are obt…

Modeling Hypergraph Using Large Language Models

2025-10-09 · Bingqiao Gu, Jiale Zeng, Xingqin Qi, Dong Li arxiv

Due to the advantages of hypergraphs in modeling high-order relationships in complex systems, they have been applied to higher-order clustering, hypergraph neural networks and computer vision. These applications rely hea…

Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution

2021-12-09 · Yunpeng Bai, Chen Gong, Bin Zhang, Guoliang Fan 외

Recent years have witnessed the great success of multi-agent systems (MAS). Value decomposition, which decomposes joint action values into individual action values, has been an important work in MAS. However, many value …

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+4

Finite-Time Frequentist Regret Bounds of Multi-Agent Thompson Sampling on Sparse Hypergraphs

2023-12-24 · Tianyuan Jin, Hao-Lun Hsu, William Chang, Pan Xu

We study the multi-agent multi-armed bandit (MAMAB) problem, where $m$ agents are factored into $\rho$ overlapping groups. Each group represents a hyperedge, forming a hypergraph over the agents. At each round of interac…

Computational Efficiency Thompson Sampling