Vision Transformerは画像ベース強化学習でCNNに勝てるか?
Evaluating Vision Transformer Methods for Deep Reinforcement Learning from Pixels
画像入力の強化学習制御タスクでViTの学習手法を評価し、CNNベースのRADと比較した。補助タスクはViTの性能を向上させるが、総合的にはCNNが優位であることを示した。
著者: Tianxin Tao, Daniele Reda, Michiel van de Panne
分類: cs.LG, cs.CV, cs.RO
原文アブストラクト
Vision Transformers (ViT) have recently demonstrated the significant potential of transformer architectures for computer vision. To what extent can image-based deep reinforcement learning also benefit from ViT architectures, as compared to standard convolutional neural network (CNN) architectures? To answer this question, we evaluate ViT training methods for image-based reinforcement learning (RL) control tasks and compare these results to a leading convolutional-network architecture method, RAD. For training the ViT encoder, we consider several recently-proposed self-supervised losses that are treated as auxiliary tasks, as well as a baseline with no additional loss terms. We find that the CNN architectures trained using RAD still generally provide superior performance. For the ViT methods, all three types of auxiliary tasks that we consider provide a benefit over plain ViT training. Furthermore, ViT reconstruction-based tasks are found to significantly outperform ViT contrastive-learning.
