Skip to the main content

Original scientific paper

https://doi.org/10.52685/cjp.22.66.5

Machine Learning, Functions and Goals

Patrick Butlin orcid id orcid.org/0000-0001-5837-5057 ; University of Oxford, Oxford, UK


Full text: english pdf 164 Kb

page 351-370

downloads: 636

cite


Abstract

Machine learning researchers distinguish between reinforcement learning and supervised learning and refer to reinforcement learning systems as “agents”. This paper vindicates the claim that systems trained by reinforcement learning are agents while those trained by supervised learning are not. Systems of both kinds satisfy Dretske’s criteria for agency, because they both learn to produce outputs selectively in response to inputs. However, reinforcement learning is sensitive to the instrumental value of outputs, giving rise to systems which exploit the effects of outputs on subsequent inputs to achieve good performance over episodes of interaction with their environments. Supervised learning systems, in contrast, merely learn to produce better outputs in response to individual inputs.

Keywords

Agency; machine learning; reinforcement learning; artificial intelligence; Dretske.

Hrčak ID:

288525

URI

https://hrcak.srce.hr/288525

Publication date:

27.12.2022.

Visits: 1.682 *