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...
Guardado en:
Autores principales: | Agrim Gupta, Silvio Savarese, Surya Ganguli, Li Fei-Fei |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/4dd31838732842439cc1301e52613d1c |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Translating Embodied Cognition for Embodied Learning in the Classroom
por: Sheila L. Macrine, et al.
Publicado: (2021) -
Embodied Intelligence in Soft Robotics Through Hardware Multifunctionality
por: Matteo Cianchetti, et al.
Publicado: (2021) -
Embodied learning via a knowledge concert: An exploratory intervention study
por: Eva Bojner Horwitz, et al.
Publicado: (2021) -
Automated curriculum learning for embodied agents a neuroevolutionary approach
por: Nicola Milano, et al.
Publicado: (2021) -
Avian extremity reconstruction via osseointegrated leg-prosthesis for intuitive embodiment
por: Sarah Hochgeschurz, et al.
Publicado: (2021)