Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
ICLR 2021, 2021.
The first successful demonstration that image augmentation can be applied to image-based Deep RL to achieve SOTA performance.
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
PPT (Upload PPT)