@article{alyapunovdriftpluspenaltymethodtailored,
  title = {A Lyapunov Drift-Plus-Penalty Method Tailored for Reinforcement Learning with Queue Stability},
  author = {Wenhan Xu and Jiashuo Jiang and Lei Deng and Danny Hin-Kwok Tsang},
  year = {2025},
  eprint = {2506.04291},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.04291v1},
}