Embodied intelligence via learning and evolution

The authors propose a new framework, deep evolutionary reinforcement learning, evolves agents with diverse morphologies to learn hard locomotion and manipulation tasks in complex environments, and reveals insights into relations between environmental physics, embodied intelligence, and the evolution...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Agrim Gupta, Silvio Savarese, Surya Ganguli, Li Fei-Fei
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Science Q
Acceso en línea:	https://doaj.org/article/4dd31838732842439cc1301e52613d1c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4dd31838732842439cc1301e52613d1c
record_format	dspace
spelling	oai:doaj.org-article:4dd31838732842439cc1301e52613d1c2021-12-02T19:16:12ZEmbodied intelligence via learning and evolution10.1038/s41467-021-25874-z2041-1723https://doaj.org/article/4dd31838732842439cc1301e52613d1c2021-10-01T00:00:00Zhttps://doi.org/10.1038/s41467-021-25874-zhttps://doaj.org/toc/2041-1723The authors propose a new framework, deep evolutionary reinforcement learning, evolves agents with diverse morphologies to learn hard locomotion and manipulation tasks in complex environments, and reveals insights into relations between environmental physics, embodied intelligence, and the evolution of rapid learning.Agrim GuptaSilvio SavareseSurya GanguliLi Fei-FeiNature PortfolioarticleScienceQENNature Communications, Vol 12, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Science Q
spellingShingle	Science Q Agrim Gupta Silvio Savarese Surya Ganguli Li Fei-Fei Embodied intelligence via learning and evolution
description	The authors propose a new framework, deep evolutionary reinforcement learning, evolves agents with diverse morphologies to learn hard locomotion and manipulation tasks in complex environments, and reveals insights into relations between environmental physics, embodied intelligence, and the evolution of rapid learning.
format	article
author	Agrim Gupta Silvio Savarese Surya Ganguli Li Fei-Fei
author_facet	Agrim Gupta Silvio Savarese Surya Ganguli Li Fei-Fei
author_sort	Agrim Gupta
title	Embodied intelligence via learning and evolution
title_short	Embodied intelligence via learning and evolution
title_full	Embodied intelligence via learning and evolution
title_fullStr	Embodied intelligence via learning and evolution
title_full_unstemmed	Embodied intelligence via learning and evolution
title_sort	embodied intelligence via learning and evolution
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/4dd31838732842439cc1301e52613d1c
work_keys_str_mv	AT agrimgupta embodiedintelligencevialearningandevolution AT silviosavarese embodiedintelligencevialearningandevolution AT suryaganguli embodiedintelligencevialearningandevolution AT lifeifei embodiedintelligencevialearningandevolution
_version_	1718376968864399360

Embodied intelligence via learning and evolution

Ejemplares similares