A micro-genesis account of longer-form reinforcement learning in structured and unstructured environments

We explored the possibility that in order for longer-form expressions of reinforcement learning (win-calmness, loss-restlessness) to manifest across tasks, they must first develop because of micro-transactions within tasks. We found no evidence of win-calmness or loss-restlessness when wins could no...

Descripción completa

Detalles Bibliográficos
Autores principales: Dyson, Benjamin James, Asad, Ahad
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2021
Materias:
Brief Communication
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8222288/
https://www.ncbi.nlm.nih.gov/pubmed/34162885
http://dx.doi.org/10.1038/s41539-021-00098-4
_version_ 1783711462952271872
author Dyson, Benjamin James
Asad, Ahad
author_facet Dyson, Benjamin James
Asad, Ahad
author_sort Dyson, Benjamin James
collection PubMed
description We explored the possibility that in order for longer-form expressions of reinforcement learning (win-calmness, loss-restlessness) to manifest across tasks, they must first develop because of micro-transactions within tasks. We found no evidence of win-calmness or loss-restlessness when wins could not be maximised (unexploitable opponents), nor when the threat of win minimisation was presented (exploiting opponents), but evidence of win-calmness (but not loss-restlessness) when wins could be maximised (exploitable opponents).
format Online
Article
Text
id pubmed-8222288
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-82222882021-07-09 A micro-genesis account of longer-form reinforcement learning in structured and unstructured environments Dyson, Benjamin James Asad, Ahad NPJ Sci Learn Brief Communication We explored the possibility that in order for longer-form expressions of reinforcement learning (win-calmness, loss-restlessness) to manifest across tasks, they must first develop because of micro-transactions within tasks. We found no evidence of win-calmness or loss-restlessness when wins could not be maximised (unexploitable opponents), nor when the threat of win minimisation was presented (exploiting opponents), but evidence of win-calmness (but not loss-restlessness) when wins could be maximised (exploitable opponents). Nature Publishing Group UK 2021-06-23 /pmc/articles/PMC8222288/ /pubmed/34162885 http://dx.doi.org/10.1038/s41539-021-00098-4 Text en © The Author(s) 2021 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as 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. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Brief Communication
Dyson, Benjamin James
Asad, Ahad
A micro-genesis account of longer-form reinforcement learning in structured and unstructured environments
title A micro-genesis account of longer-form reinforcement learning in structured and unstructured environments
title_full A micro-genesis account of longer-form reinforcement learning in structured and unstructured environments
title_fullStr A micro-genesis account of longer-form reinforcement learning in structured and unstructured environments
title_full_unstemmed A micro-genesis account of longer-form reinforcement learning in structured and unstructured environments
title_short A micro-genesis account of longer-form reinforcement learning in structured and unstructured environments
title_sort micro-genesis account of longer-form reinforcement learning in structured and unstructured environments
topic Brief Communication
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8222288/
https://www.ncbi.nlm.nih.gov/pubmed/34162885
http://dx.doi.org/10.1038/s41539-021-00098-4
work_keys_str_mv AT dysonbenjaminjames amicrogenesisaccountoflongerformreinforcementlearninginstructuredandunstructuredenvironments
AT asadahad amicrogenesisaccountoflongerformreinforcementlearninginstructuredandunstructuredenvironments
AT dysonbenjaminjames microgenesisaccountoflongerformreinforcementlearninginstructuredandunstructuredenvironments
AT asadahad microgenesisaccountoflongerformreinforcementlearninginstructuredandunstructuredenvironments

Ejemplares similares