Automated curriculum learning for embodied agents a neuroevolutionary approach
Abstract We demonstrate how the evolutionary training of embodied agents can be extended with a curriculum learning algorithm that automatically selects the environmental conditions in which the evolving agents are evaluated. The environmental conditions are selected to adjust the level of difficult...
Guardado en:
Autores principales: | Nicola Milano, Stefano Nolfi |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/526589e900f34ccc951da87100eb776a |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Adaptation to criticality through organizational invariance in embodied agents
por: Miguel Aguilera, et al.
Publicado: (2018) -
Translating Embodied Cognition for Embodied Learning in the Classroom
por: Sheila L. Macrine, et al.
Publicado: (2021) -
Embodied intelligence via learning and evolution
por: Agrim Gupta, et al.
Publicado: (2021) -
A machine learning approach to automated structural network analysis: application to neonatal encephalopathy.
por: Etay Ziv, et al.
Publicado: (2013) -
Reachability and the sense of embodiment in amputees using prostheses
por: Adrienne Gouzien, et al.
Publicado: (2017)