@inproceedings{rudderreturndecompositionfordelayed,
  title = {RUDDER: Return Decomposition for Delayed Rewards},
  author = {Jose A. Arjona-Medina and Michael Gillhofer and Michael Widrich and Thomas Unterthiner and Johannes Brandstetter and Sepp Hochreiter},
  year = {2018},
  booktitle = {NeurIPS 2019 12},
  eprint = {1806.07857},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1806.07857v3},
}