@article{rewardweightedregressionconvergestoa,
  title = {Reward-Weighted Regression Converges to a Global Optimum},
  author = {Miroslav Štrupl and Francesco Faccio and Dylan R. Ashley and Rupesh Kumar Srivastava and Jürgen Schmidhuber},
  year = {2021},
  eprint = {2107.09088},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2107.09088v3},
}