Scalar reward is not enough: A response to Silver, Singh, Precup and Sutton (2021)

The recent paper `"Reward is Enough" by Silver, Singh, Precup and Sutton posits that the concept of reward maximisation is sufficient to underpin all intelligence, both natural and artificial. We contest the underlying assumption of Silver et al. that such reward can be scalar-valued. In t...

Full description

Saved in:
Bibliographic Details
Main Authors Vamplew, Peter, Smith, Benjamin J, Kallstrom, Johan, Ramos, Gabriel, Radulescu, Roxana, Roijers, Diederik M, Hayes, Conor F, Heintz, Fredrik, Mannion, Patrick, Libin, Pieter J. K, Dazeley, Richard, Foale, Cameron
Format Journal Article
LanguageEnglish
Published 24.11.2021
Subjects
Computer Science - Artificial Intelligence
Online AccessGet full text

Cover

More Information
Summary:The recent paper `"Reward is Enough" by Silver, Singh, Precup and Sutton posits that the concept of reward maximisation is sufficient to underpin all intelligence, both natural and artificial. We contest the underlying assumption of Silver et al. that such reward can be scalar-valued. In this paper we explain why scalar rewards are insufficient to account for some aspects of both biological and computational intelligence, and argue in favour of explicitly multi-objective models of reward maximisation. Furthermore, we contend that even if scalar reward functions can trigger intelligent behaviour in specific cases, it is still undesirable to use this approach for the development of artificial general intelligence due to unacceptable risks of unsafe or unethical behaviour.
DOI:10.48550/arxiv.2112.15422