Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems

Part of Advances in Neural Information Processing Systems 34 (NeurIPS 2021)

Bibtex Paper Reviews And Public Comment » Supplemental


Wenqing Zheng, Qiangqiang Guo, Hao Yang, Peihao Wang, Zhangyang Wang


Multi-agent control is a central theme in the Cyber-Physical Systems (CPS). However, current control methods either receive non-Markovian states due to insufficient sensing and decentralized design, or suffer from poor convergence. This paper presents the Delayed Propagation Transformer (DePT), a new transformer-based model that specializes in the global modeling of CPS while taking into account the immutable constraints from the physical world. DePT induces a cone-shaped spatial-temporal attention prior, which injects the information propagation and aggregation principles and enables a global view. With physical constraint inductive bias baked into its design, our DePT is ready to plug and play for a broad class of multi-agent systems. The experimental results on one of the most challenging CPS -- network-scale traffic signal control system in the open world -- show that our model outperformed the state-of-the-art expert methods on synthetic and real-world datasets. Our codes are released at: