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

Yarats Denis
Yarats Denis

international conference on learning representations, 2020.

Cited by: 0|Views23

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 regularize the value funct...More

Code:

Data:

Your rating :
0

 

Tags
Comments