Cargando…
What’s a good prediction? Challenges in evaluating an agent’s knowledge
Constructing general knowledge by learning task-independent models of the world can help agents solve challenging problems. However, both constructing and evaluating such models remain an open challenge. The most common approaches to evaluating models is to assess their accuracy with respect to obse...
Autores principales: | Kearney, Alex, Koop, Anna J, Pilarski, Patrick M |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
SAGE Publications
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10240643/ https://www.ncbi.nlm.nih.gov/pubmed/37284424 http://dx.doi.org/10.1177/10597123221095880 |
Ejemplares similares
-
Prediction, Knowledge, and Explainability: Examining the Use of General Value Functions in Machine Knowledge
por: Kearney, Alex, et al.
Publicado: (2022) -
Examining the Use of Temporal-Difference Incremental Delta-Bar-Delta for Real-World Predictive Knowledge Architectures
por: Günther, Johannes, et al.
Publicado: (2020) -
Predictive tools in psychosis: what is ‘good enough’?
por: Seyedsalehi, Aida, et al.
Publicado: (2023) -
What's good for the gander may not be good for the goose.
por: Kornblum, A
Publicado: (1993) -
What Is the Good of the College?
Publicado: (1920)