A micro-genesis account of longer-form reinforcement learning in structured and unstructured environments

Abstract We explored the possibility that in order for longer-form expressions of reinforcement learning (win-calmness, loss-restlessness) to manifest across tasks, they must first develop because of micro-transactions within tasks. We found no evidence of win-calmness or loss-restlessness when wins...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Benjamin James Dyson, Ahad Asad
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
Acceso en línea:https://doaj.org/article/33817a89c1e843b6b05a2e070cb42185
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Descripción
Sumario:Abstract We explored the possibility that in order for longer-form expressions of reinforcement learning (win-calmness, loss-restlessness) to manifest across tasks, they must first develop because of micro-transactions within tasks. We found no evidence of win-calmness or loss-restlessness when wins could not be maximised (unexploitable opponents), nor when the threat of win minimisation was presented (exploiting opponents), but evidence of win-calmness (but not loss-restlessness) when wins could be maximised (exploitable opponents).