Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels

Denis Yarats
Denis Yarats

ICLR 2021, 2021.

Cited by: 1|Views31
Weibo:
The first successful demonstration that image augmentation can be applied to image-based Deep RL to achieve SOTA performance.

Abstract:

We propose a simple data augmentation technique that can be applied to standard model-free reinforcement learning algorithms, enabling robust learning directly from pixels without the need for auxiliary losses or pre-training. The approach leverages input perturbations commonly used in computer vision tasks to transform input examples, a...More
0
Full Text
Bibtex
Weibo
Your rating :
0

 

Tags
Comments