Journal article
Reinforcement learning and artificial agency
- Abstract:
- There is an apparent connection between reinforcement learning and agency. In computer science 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 paper examines this connection, focusing on artificial reinforcement learning systems and working from the assumption that there are a range of 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.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Version of record, pdf, 1020.0KB, Terms of use)
-
- Publisher copy:
- 10.1111/mila.12458
Authors
- Publisher:
- Wiley
- Journal:
- Mind and Language More from this journal
- Volume:
- 39
- Issue:
- 1
- Pages:
- 22-38
- Publication date:
- 2023-05-12
- Acceptance date:
- 2023-04-06
- DOI:
- EISSN:
-
1468-0017
- ISSN:
-
0268-1064
- Language:
-
English
- Keywords:
- Pubs id:
-
1337624
- Local pid:
-
pubs:1337624
- Deposit date:
-
2023-04-17
Terms of use
- Copyright holder:
- Patrick Butlin
- Copyright date:
- 2023
- Rights statement:
- © 2023 The Author. Mind & Language published by John Wiley & Sons Ltd. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.
- Licence:
- CC Attribution (CC BY)
If you are the owner of this record, you can report an update to it here: Report update to this record