Keywords: Deep Reinforcement Learning, Transformers, Self-Supervised Learning, Pre-training
Abstract: The Vision Transformer architecture has shown to be competitive in the computer vision (CV) space where it has dethroned convolution-based networks in several benchmarks. Nevertheless, Convolutional Neural Networks (CNN) remain the preferential architecture for the representation module in Reinforcement Learning. In this work, we study pretraining a Vision Transformer using several state-of-the-art self-supervised methods and assess data-efficiency gains from this training framework. We propose a new self-supervised learning method called TOV-VICReg that extends VICReg to better capture temporal relations between observations by adding a temporal order verification task. Furthermore, we evaluate the resultant encoders with Atari games in a sample-efficiency regime. Our results show that the vision transformer, when pretrained with TOV-VICReg, outperforms the other self-supervised methods but still struggles to overcome a CNN. Nevertheless, we were able to outperform a CNN in two of the ten games where we perform a 100k steps evaluation. Ultimately, we believe that such approaches in Deep Reinforcement Learning (DRL) might be the key to achieving new levels of performance as seen in natural language processing and computer vision.
Supplementary Material: zip