@article{upsidedownreinforcementlearningcan,
  title = {Upside-Down Reinforcement Learning Can Diverge in Stochastic Environments With Episodic Resets},
  author = {Miroslav Štrupl and Francesco Faccio and Dylan R. Ashley and Jürgen Schmidhuber and Rupesh Kumar Srivastava},
  year = {2022},
  eprint = {2205.06595},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2205.06595v1},
}