Data Augmentation for Reinforcement Learning Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Essential papers on data augmentation for RL — from random crops and color jitter to automatic augmentation discovery for sample-efficient visual control.

Data Augmentation for Reinforcement Learning: 10 key papers

1. Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
   Kostrikov et al. arXiv 2020.
2. Reinforcement Learning with Augmented Data
   Laskin et al. arXiv 2020.
3. CURL: Contrastive Unsupervised Representations for Reinforcement Learning
   Srinivas et al. arXiv 2020.
4. Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning
   Yarats et al. arXiv 2021.
5. Automatic Data Augmentation for Generalization in Deep Reinforcement Learning
   Raileanu et al. arXiv 2020.
6. Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation
   Hansen et al. arXiv 2021.
7. Generalization in Reinforcement Learning by Soft Data Augmentation
   Hansen and Wang. arXiv 2020.
8. Improving Generalization in Reinforcement Learning with Mixture Regularization
   Wang et al. arXiv 2020.
9. Don't Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning
   Yuan et al. arXiv 2022.
10. Data-Efficient Reinforcement Learning with Self-Predictive Representations
    Schwarzer et al. arXiv 2020.

Related reading lists

• Contrastive & Self-Supervised Learning
• Vision-Language Models & Multimodal Learning
• World Models and Model-Based RL
• Representation Learning for RL
• Preference Learning & Learning from Comparisons
• Transformers for Sequential Decision Making
• Reasoning in LLMs
• Intrinsic Motivation & Empowerment