@article{alignrudderlearningfromfewdemonstrations,
  title = {Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution},
  author = {Vihang P. Patil and Markus Hofmarcher and Marius-Constantin Dinu and Matthias Dorfer and Patrick M. Blies and Johannes Brandstetter and Jose A. Arjona-Medina and Sepp Hochreiter},
  year = {2020},
  eprint = {2009.14108},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2009.14108v2},
}