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.
Paper
References (53)
01On the Expressivity of Multidimensional Markov RewardShuwa Miura2023 · arXiv.org · 6 citations In Library
04Abstractions of General Reinforcement LearningSultan Javed Majeed2021 · arXiv.org · 8 citations In Library
Scroll for more · 38 remaining