@article{optimalmanagementofthepeakpowerpenalty,
  title = {Optimal Management of the Peak Power Penalty for Smart Grids Using MPC-based Reinforcement Learning},
  author = {WenQi Cai and Hossein N. Esfahani and Arash B. Kordabad and Sébastien Gros},
  year = {2021},
  eprint = {2108.01459},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2108.01459v2},
}