Inverse Reinforcement Learning with Graph Neural Networks for IoT Resource Allocation

Guangchen Wang; Peng Cheng; Zhuo Chen; Wei Xiang; Branka Vucetic; Yonghui Li

ICASSP 2023accepted0 citations

Inverse Reinforcement Learning with Graph Neural Networks for IoT Resource Allocation

Guangchen Wang, Peng Cheng, Zhuo Chen, Wei Xiang, Branka Vucetic, Yonghui Li

Abstract

The rapid development of Internet of Things (IoT) applications requires efficient computing and communication resource allocation strategies to streamline the existing network operations. These strategies could be formulated as mixed-integer nonlinear programming (MINLP) problems, where the optimal branch-and-bound (B&B) with the full strong branching (FSB) variable selection policy features an extremely high complexity. We propose inverse reinforcement learning with graph neural networks (GNNIRL) to generate a new variable selection policy that closely matches the FSB variable selection. Without sacrificing the optimality, the GNNIRL can directly infer the variable selection with a significantly lower complexity, which is also verified by simulation.

BibTeX

@inproceedings{icassp2023_inversereinforce,
  title = {Inverse Reinforcement Learning with Graph Neural Networks for IoT Resource Allocation},
  author = {Guangchen Wang and Peng Cheng and Zhuo Chen and Wei Xiang and Branka Vucetic and Yonghui Li},
  booktitle = {ICASSP 2023},
  year = {2023}
}