Model-free reinforcement learning for robust locomotion using demonstrations from trajectory optimization

We present a general, two-stage reinforcement learning approach to create robust policies that can be deployed on real robots without any additional training using a single demonstration generated by trajectory optimization. The demonstration is used in the first stage as a starting point to facilit...

Descripción completa

Detalles Bibliográficos
Autores principales: Bogdanovic, Miroslav, Khadiv , Majid, Righetti , Ludovic
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Robotics and AI
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9484268/
https://www.ncbi.nlm.nih.gov/pubmed/36134338
http://dx.doi.org/10.3389/frobt.2022.854212

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9484268/
https://www.ncbi.nlm.nih.gov/pubmed/36134338
http://dx.doi.org/10.3389/frobt.2022.854212

Ejemplares similares