Visual Pretraining via Contrastive Predictive Model for Pixel-Based Reinforcement Learning

In an attempt to overcome the limitations of reward-driven representation learning in vision-based reinforcement learning (RL), an unsupervised learning framework referred to as the visual pretraining via contrastive predictive model (VPCPM) is proposed to learn the representations detached from the...

Descripción completa

Detalles Bibliográficos
Autores principales: Luu, Tung M., Vu, Thang, Nguyen, Thanh, Yoo, Chang D.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9460564/
https://www.ncbi.nlm.nih.gov/pubmed/36080961
http://dx.doi.org/10.3390/s22176504

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9460564/
https://www.ncbi.nlm.nih.gov/pubmed/36080961
http://dx.doi.org/10.3390/s22176504

Ejemplares similares