Quantifying Reinforcement-Learning Agent’s Autonomy, Reliance on Memory and Internalisation of the Environment

Intuitively, the level of autonomy of an agent is related to the degree to which the agent’s goals and behaviour are decoupled from the immediate control by the environment. Here, we capitalise on a recent information-theoretic formulation of autonomy and introduce an algorithm for calculating auton...

Descripción completa

Detalles Bibliográficos
Autores principales: Ingel, Anti, Makkeh, Abdullah, Corcoll, Oriol, Vicente, Raul
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947692/
https://www.ncbi.nlm.nih.gov/pubmed/35327912
http://dx.doi.org/10.3390/e24030401

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947692/
https://www.ncbi.nlm.nih.gov/pubmed/35327912
http://dx.doi.org/10.3390/e24030401

Ejemplares similares