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

Abstract 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...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Benjamin James Dyson, Ahad Asad
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Special aspects of education LC8-6691 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/33817a89c1e843b6b05a2e070cb42185
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:33817a89c1e843b6b05a2e070cb42185
record_format	dspace
spelling	oai:doaj.org-article:33817a89c1e843b6b05a2e070cb421852021-12-02T17:45:10ZA micro-genesis account of longer-form reinforcement learning in structured and unstructured environments10.1038/s41539-021-00098-42056-7936https://doaj.org/article/33817a89c1e843b6b05a2e070cb421852021-06-01T00:00:00Zhttps://doi.org/10.1038/s41539-021-00098-4https://doaj.org/toc/2056-7936Abstract 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).Benjamin James DysonAhad AsadNature PortfolioarticleSpecial aspects of educationLC8-6691Neurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENnpj Science of Learning, Vol 6, Iss 1, Pp 1-5 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Special aspects of education LC8-6691 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	Special aspects of education LC8-6691 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Benjamin James Dyson Ahad Asad A micro-genesis account of longer-form reinforcement learning in structured and unstructured environments
description	Abstract 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	article
author	Benjamin James Dyson Ahad Asad
author_facet	Benjamin James Dyson Ahad Asad
author_sort	Benjamin James Dyson
title	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_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_sort	micro-genesis account of longer-form reinforcement learning in structured and unstructured environments
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/33817a89c1e843b6b05a2e070cb42185
work_keys_str_mv	AT benjaminjamesdyson amicrogenesisaccountoflongerformreinforcementlearninginstructuredandunstructuredenvironments AT ahadasad amicrogenesisaccountoflongerformreinforcementlearninginstructuredandunstructuredenvironments AT benjaminjamesdyson microgenesisaccountoflongerformreinforcementlearninginstructuredandunstructuredenvironments AT ahadasad microgenesisaccountoflongerformreinforcementlearninginstructuredandunstructuredenvironments
_version_	1718379578413547520

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

Ejemplares similares