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

May 21, 2021 (edited Dec 22, 2021)NeurIPS 2021 PosterReaders: Everyone
  • Keywords: Transformers, Control, Reinforcement Learning, Cyber-Physical System
  • TL;DR: This paper established a centralized multi-agent control scheme, using modified and improved transformer architecture.
  • Abstract: 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: https://github.com/VITA-Group/DePT.
  • Supplementary Material: zip
  • Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
  • Code: https://github.com/VITA-Group/DePT
18 Replies

Loading