@article{exploitingthesignoftheadvantagefunction,
  title = {Exploiting the Sign of the Advantage Function to Learn Deterministic Policies in Continuous Domains},
  author = {Matthieu Zimmer and Paul Weng},
  year = {2019},
  eprint = {1906.04556},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1906.04556v2},
}