Settling the Reward Hypothesis

Abstract

The reward hypothesis posits that, "all of what we mean by goals and purposes can be well thought of as maximization of the expected value of the cumulative sum of a received scalar signal (reward)." We aim to fully settle this hypothesis. This will not conclude with a simple affirmation or refutation, but rather specify completely the implicit requirements on goals and purposes under which the hypothesis holds.

Cite

Text

Bowling et al. "Settling the Reward Hypothesis." International Conference on Machine Learning, 2023.

Markdown

[Bowling et al. "Settling the Reward Hypothesis." International Conference on Machine Learning, 2023.](https://mlanthology.org/icml/2023/bowling2023icml-settling/)

BibTeX

@inproceedings{bowling2023icml-settling,
  title     = {{Settling the Reward Hypothesis}},
  author    = {Bowling, Michael and Martin, John D and Abel, David and Dabney, Will},
  booktitle = {International Conference on Machine Learning},
  year      = {2023},
  pages     = {3003-3020},
  volume    = {202},
  url       = {https://mlanthology.org/icml/2023/bowling2023icml-settling/}
}