文献类型：期刊文献

英文题名：Hybrid Mamba-Transformer Multi-Agent Reinforcement Learning for scalable coordination in complex environments

作者：Chen, Kai[1];Chen, Zhihua[1];Dai, Lei[1];Wang, Zhe[1];Chen, Xin[1]

机构：[1]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China

年份：2025

卷号：41

期号：13

起止页码：10649

外文期刊名：VISUAL COMPUTER

收录：;EI(收录号：20252718713297);WOS:【SCI-EXPANDED(收录号:WOS:001520393400001)】；

基金：This work was supported by the National Natural Science Foundation of China (Grant Nos. 62272164 and 62306113) and the Aeronautical Science Foundation of China (Grant Nos. 202400550S7003 and 202400550S7004);

语种：英文

外文关键词：Reinforcement learning; Transformer; Mamba; Multi-agent

摘要：Transformer architectures have achieved remarkable success in Multi-Agent Reinforcement Learning (MARL), particularly in graphics-driven simulation environments. However, their quadratic complexity limits scalability in scenarios with a large number of agents. In contrast, Mamba models offer an efficient alternative for sequence modeling but may underperform in tasks requiring agent coordination. In this paper, we propose the Hybrid Mamba-Transformer Multi-Agent Reinforcement Learning Algorithm (HMMA), which combines the representational strengths of Transformer-based attention with the computational efficiency of the Mamba sequence model. We evaluate HMMA in challenging StarCraft II scenarios, demonstrating faster convergence, higher mean episode rewards, and improved win rates compared to mainstream baselines. HMMA achieves a 9.5% improvement in normalized mean episode reward and a 19.9% increase in win rate over the Multi-Agent Transformer, highlighting its potential for scalable MARL in complex environments. The related code of our method is available at https://github.com/origin-orange/HMMA.