Efficient Policy Generation in Multi-Agent Systems via Hypergraph Neural Network
This addresses collaboration problems in multi-agent systems, but appears incremental as it builds on existing actor-critic and hypergraph methods.
The paper tackles the challenge of developing sufficient collaboration between diverse agents in multi-agent reinforcement learning by proposing an algorithm that adaptively constructs hypergraph structures for agent interaction and uses hypergraph convolution networks for information extraction. Experiments show advantages over existing methods, though no specific numerical results are provided.
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.