@article{convergenceproofforactorcriticmethods1,
  title = {Convergence Proof for Actor-Critic Methods Applied to PPO and RUDDER},
  author = {Markus Holzleitner and Lukas Gruber and José Arjona-Medina and Johannes Brandstetter and Sepp Hochreiter},
  year = {2020},
  eprint = {2012.01399},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2012.01399v1},
}