Answers are grounded in this paper and cite their sources.
This article examines the link between reinforcement learning and various forms of agency in artificial systems, suggesting significant implications.
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.
No takes yet. Share an insight, caveat, or question.
Patrick Butlin (2023) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: