Model-free safe policy learning via hard action barrier functions

Agustin Castellano, Juan-Andrés Bazerque, Enrique Mallada. Model-free safe policy learning via hard action barrier functions. In 55th Annual Conference on Information Sciences and Systems, CISS 2021, Baltimore, MD, USA, March 24-26, 2021. pages 1, IEEE, 2021. [doi]

@inproceedings{CastellanoBM21,
  title = {Model-free safe policy learning via hard action barrier functions},
  author = {Agustin Castellano and Juan-Andrés Bazerque and Enrique Mallada},
  year = {2021},
  doi = {10.1109/CISS50987.2021.9400210},
  url = {https://doi.org/10.1109/CISS50987.2021.9400210},
  researchr = {https://researchr.org/publication/CastellanoBM21},
  cites = {0},
  citedby = {0},
  pages = {1},
  booktitle = {55th Annual Conference on Information Sciences and Systems, CISS 2021, Baltimore, MD, USA, March 24-26, 2021},
  publisher = {IEEE},
  isbn = {978-1-6654-1268-1},
}