Retrospective model-based inference guides model-free credit assignment
The reinforcement learning literature suggests decisions are based on a model-free system, operating retrospectively, and a model-based system, operating prospectively. Here, the authors show that a model-based retrospective inference of a reward’s cause, guides model-free credit-assignment.
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2019
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/ca9bae169c454436895a7d3764634701 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | The reinforcement learning literature suggests decisions are based on a model-free system, operating retrospectively, and a model-based system, operating prospectively. Here, the authors show that a model-based retrospective inference of a reward’s cause, guides model-free credit-assignment. |
|---|