English

Settling the Reward Hypothesis

Artificial Intelligence 2023-09-19 v2 Machine Learning Statistics Theory Statistics Theory

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.

Keywords

Cite

@article{arxiv.2212.10420,
  title  = {Settling the Reward Hypothesis},
  author = {Michael Bowling and John D. Martin and David Abel and Will Dabney},
  journal= {arXiv preprint arXiv:2212.10420},
  year   = {2023}
}
R2 v1 2026-06-28T07:45:04.037Z