Efficient Policy Generation In Multi-agent Systems Via Hypergraph Neural Network

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2022efficient

Related papers

• Cooperative Multi-agent Reinforcement Learning With Hypergraph Convolution (2021)5.84
• Cooperative Policy Learning With Pre-trained Heterogeneous Observation Representations (2020)0.00
• Hypermarl: Adaptive Hypernetworks For Multi-agent RL (2024)0.00
• Towards Heterogeneous Multi-agent Reinforcement Learning With Graph Neural Networks (2020)6.34
• Context-aware Bayesian Network Actor-critic Methods For Cooperative Multi-agent Reinforcement Learning (2023)0.00
• Fully Decentralized Multi-agent Reinforcement Learning With Networked Agents (2018)0.00
• Multi-agent Reinforcement Learning In Stochastic Networked Systems (2020)0.00
• Multi-agent Actor-critic For Mixed Cooperative-competitive Environments (2017)0.00