@article{controlrandomisationapproachforpolicy,
  title = {Control randomisation approach for policy gradient and application to reinforcement learning in optimal switching},
  author = {Robert Denkert and Huyên Pham and Xavier Warin},
  year = {2024},
  eprint = {2404.17939},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.17939v2},
}