@article{reinforcementlearningupsidedowndont,
  title = {Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions},
  author = {Juergen Schmidhuber},
  year = {2019},
  eprint = {1912.02875},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1912.02875v2},
}