Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation
arXiv:2107.00644
Abstract
While agents trained by Reinforcement Learning (RL) can solve increasingly challenging tasks directly from visual observations, generalizing learned skills to novel environments remains very challenging. Extensive use of data augmentation is a promising technique for improving generalization in RL, but it is often found to decrease sample efficiency and can even lead to divergence. In this paper, we investigate causes of instability when using data augmentation in common off-policy RL algorithms. We identify two problems, both rooted in high-variance Q-targets. Based on our findings, we propose a simple yet effective technique for stabilizing this class of algorithms under augmentation. We perform extensive empirical evaluation of image-based RL using both ConvNets and Vision Transformers (ViT) on a family of benchmarks based on DeepMind Control Suite, as well as in robotic manipulation tasks. Our method greatly improves stability and sample efficiency of ConvNets under augmentation, and achieves generalization results competitive with state-of-the-art methods for image-based RL in environments with unseen visuals. We further show that our method scales to RL with ViT-based architectures, and that data augmentation may be especially important in this setting.
Code and videos are available at https://nicklashansen.github.io/SVEA
References in corpus (14)
- A Simple Framework for Contrastive Learning of Visual Representations
- DeepMind Control Suite
- Rainbow: Combining Improvements in Deep Reinforcement Learning
- Reinforcement Learning with Augmented Data
- Gradient Surgery for Multi-Task Learning
- Learning Invariant Representations for Reinforcement Learning without Reconstruction
- Decoupling Representation Learning from Reinforcement Learning
- Self-Supervised Policy Adaptation during Deployment
- Automatic Data Augmentation for Generalization in Deep Reinforcement Learning
- Data-Efficient Reinforcement Learning with Self-Predictive Representations
- Improving Generalization in Reinforcement Learning with Mixture Regularization
- Reinforcement Learning with Prototypical Representations
- Visual Imitation Made Easy
- Unsupervised Visual Attention and Invariance for Reinforcement Learning