An Experimental Study on State Representation Extraction for Vision-Based Deep Reinforcement Learning

An Experimental Study on State Representation Extraction for Vision-Based Deep Reinforcement Learning

Scaling end-to-end learning to control robots with vision inputs is a challenging problem in the field of deep reinforcement learning (DRL). While achieving remarkable success in complex sequential tasks, vision-based DRL remains extremely data-inefficient, especially when dealing with high-dimensio...

Full description

Bibliographic Details
Main Authors: Junkai Ren, Yujun Zeng, Sihang Zhou, Yichuan Zhang
Format: Article
Language:English
Published: MDPI AG 2021-11-01
Series:Applied Sciences
Subjects:
deep reinforcement learning
representation learning
unsupervised learning
feature embedding
end-to-end learning
Online Access:https://www.mdpi.com/2076-3417/11/21/10337

Internet

https://www.mdpi.com/2076-3417/11/21/10337

Similar Items