Settling the Reward Hypothesis

Published: 24 Apr 2023, Last Modified: 16 Jun 2023ICML 2023 OralPosterEveryoneRevisions
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.
Submission Number: 2261