QTypeMix: Enhancing multi-agent cooperative strategies through heterogeneous and homogeneous value decomposition

• Published in: Neural networks 2025-04, Vol.184, p.107093, Article 107093
• Main Authors: Fu, Songchen, Zhao, Shaojing, Li, Ta, Yan, Yonghong
• Format: Article
• Language: English
• Subjects: Heterogeneous agents; Markov decision process; Multi-agent reinforcement learning; Value function factorization
• ISSN: 0893-6080; 1879-2782; 1879-2782
• DOI: 10.1016/j.neunet.2024.107093

In multi-agent cooperative tasks, the presence of heterogeneous agents is familiar. Compared to cooperation among homogeneous agents, collaboration requires considering the best-suited sub-tasks for each agent. However, the operation of multi-agent systems often involves a large amount of complex interaction information, making it more challenging to learn heterogeneous strategies. Related multi-agent reinforcement learning methods sometimes use grouping mechanisms to form smaller cooperative groups or leverage prior domain knowledge to learn strategies for different roles. In contrast, agents should learn deeper role features without relying on additional information. Therefore, we propose QTypeMix, which divides the value decomposition process into homogeneous and heterogeneous stages. QTypeMix learns to extract type features from local historical observations through the TE loss. In addition, we introduce advanced network structures containing attention mechanisms and hypernets to enhance the representation capability and achieve the value decomposition process. The results of testing the proposed method on 14 maps from SMAC and SMACv2 show that QTypeMix achieves state-of-the-art performance in tasks of varying difficulty.