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.
@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}
}