Optimizing agent behavior over long time scales by transporting value
People are able to mentally time travel to distant memories and reflect on the consequences of those past events. Here, the authors show how a mechanism that connects learning from delayed rewards with memory retrieval can enable AI agents to discover links between past events to help decide better...
Guardado en:
Autores principales: | Chia-Chun Hung, Timothy Lillicrap, Josh Abramson, Yan Wu, Mehdi Mirza, Federico Carnevale, Arun Ahuja, Greg Wayne |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2019
|
Materias: | |
Acceso en línea: | https://doaj.org/article/2e805e7216b343f9a8b03a4f5ce02aad |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Over 150 Years of Long-Term Fertilization Alters Spatial Scaling of Microbial Biodiversity
por: Yuting Liang, et al.
Publicado: (2015) -
Sharp rises in large-scale, long-duration precipitation extremes with higher temperatures over Japan
por: Daisuke Hatsuzuka, et al.
Publicado: (2021) -
Hierarchical motor control in mammals and machines
por: Josh Merel, et al.
Publicado: (2019) -
Long-Term Study on Medium-Scale Traveling Ionospheric Disturbances Observed over the South American Equatorial Region
por: Patrick Essien, et al.
Publicado: (2021) -
Coordinate-Descent Adaptation over Hamiltonian Multi-Agent Networks
por: Azam Khalili, et al.
Publicado: (2021)