Reinforcement learning and artificial agency
Mind & Language · 2024-02 · 39 (1) · 22-38
DOI: 10.1111/mila.12458 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mind & Language, online erschienen am 12.05.2023. Verfasst von Patrick Butlin. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
There is an apparent connection between reinforcement learning and agency. Artificial entities controlled by reinforcement learning algorithms are standardly referred to as agents, and the mainstream view in the psychology and neuroscience of agency is that humans and other animals are reinforcement learners. This article examines this connection, focusing on artificial reinforcement learning systems and assuming that there are various forms of agency. Artificial reinforcement learning systems satisfy plausible conditions for minimal agency, and those which use models of the environment to perform forward search are capable of a form of agency which may reasonably be called action for reasons.
Zitieren
APA
Butlin, P. (2024). Reinforcement learning and artificial agency. Mind & Language, 39(1), 22-38. https://doi.org/10.1111/mila.12458
Vancouver
Butlin P. Reinforcement learning and artificial agency. Mind & Language. 2024;39(1):22-38. doi:10.1111/mila.12458
BibTeX
@article{Butlin2024,
author = {Butlin, Patrick},
title = {Reinforcement learning and artificial agency},
journal = {Mind & Language},
year = {2024},
volume = {39},
number = {1},
pages = {22--38},
doi = {10.1111/mila.12458}
}
EUVIMED