Knowledge- and ambiguity-aware robot learning from corrective and evaluative feedback

In order to deploy robots that could be adapted by non-expert users, interactive imitation learning (IIL) methods must be flexible regarding the interaction preferences of the teacher and avoid assumptions of perfect teachers (oracles), while considering they make mistakes influenced by diverse huma...

Descripción completa

Detalles Bibliográficos
Autores principales: Celemin, Carlos, Kober, Jens
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer London 2023
Materias:
S.I.: Human-aligned Reinforcement Learning for Autonomous Agents and Robots
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10338625/
https://www.ncbi.nlm.nih.gov/pubmed/37455835
http://dx.doi.org/10.1007/s00521-022-08118-z

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10338625/
https://www.ncbi.nlm.nih.gov/pubmed/37455835
http://dx.doi.org/10.1007/s00521-022-08118-z

Ejemplares similares