Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
international conference on learning representations, 2020.
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
PPT (Upload PPT)