Optimal Behavior is Easier to Learn than the Truth

We consider a reinforcement learning setting where the learner is given a set of possible models containing the true model. While there are algorithms that are able to successfully learn optimal behavior in this setting, they do so without trying to identify the underlying true model. Indeed, we sho...

Descripción completa

Detalles Bibliográficos
Autor principal: Ortner, Ronald
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer Netherlands 2016
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5018263/
https://www.ncbi.nlm.nih.gov/pubmed/27682861
http://dx.doi.org/10.1007/s11023-016-9389-y
_version_ 1782452884977221632
author Ortner, Ronald
author_facet Ortner, Ronald
author_sort Ortner, Ronald
collection PubMed
description We consider a reinforcement learning setting where the learner is given a set of possible models containing the true model. While there are algorithms that are able to successfully learn optimal behavior in this setting, they do so without trying to identify the underlying true model. Indeed, we show that there are cases in which the attempt to find the true model is doomed to failure.
format Online
Article
Text
id pubmed-5018263
institution National Center for Biotechnology Information
language English
publishDate 2016
publisher Springer Netherlands
record_format MEDLINE/PubMed
spelling pubmed-50182632016-09-26 Optimal Behavior is Easier to Learn than the Truth Ortner, Ronald Minds Mach (Dordr) Article We consider a reinforcement learning setting where the learner is given a set of possible models containing the true model. While there are algorithms that are able to successfully learn optimal behavior in this setting, they do so without trying to identify the underlying true model. Indeed, we show that there are cases in which the attempt to find the true model is doomed to failure. Springer Netherlands 2016-02-03 2016 /pmc/articles/PMC5018263/ /pubmed/27682861 http://dx.doi.org/10.1007/s11023-016-9389-y Text en © The Author(s) 2016 Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
spellingShingle Article
Ortner, Ronald
Optimal Behavior is Easier to Learn than the Truth
title Optimal Behavior is Easier to Learn than the Truth
title_full Optimal Behavior is Easier to Learn than the Truth
title_fullStr Optimal Behavior is Easier to Learn than the Truth
title_full_unstemmed Optimal Behavior is Easier to Learn than the Truth
title_short Optimal Behavior is Easier to Learn than the Truth
title_sort optimal behavior is easier to learn than the truth
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5018263/
https://www.ncbi.nlm.nih.gov/pubmed/27682861
http://dx.doi.org/10.1007/s11023-016-9389-y
work_keys_str_mv AT ortnerronald optimalbehavioriseasiertolearnthanthetruth

Ejemplares similares