# Learning Visual Robotic Control Efficiently with Contrastive Pre-training and Data Augmentation

arXiv: https://arxiv.org/abs/2012.07975 · HTML: https://mlsanity.com/paper/2012.07975/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2020.

## Built on by (most cited first, 21 of 21)

- [Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals](https://mlsanity.com/paper/2407.05996/) (2024)
- [Imitation Bootstrapped Reinforcement Learning](https://mlsanity.com/paper/2311.02198/) (2023)
- [Robot Learning with Sensorimotor Pre-training](https://mlsanity.com/paper/2306.10007/) (2023)
- [The Power of the Senses: Generalizable Manipulation from Vision and Touch through Masked Multimodal Learning](https://mlsanity.com/paper/2311.00924/) (2023)
- [Continuous Control with Coarse-to-fine Reinforcement Learning](https://mlsanity.com/paper/2407.07787/) (2024)
- [SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning](https://mlsanity.com/paper/2301.11520/) (2023)
- [Contrastive Learning for Enhancing Robust Scene Transfer in Vision-based Agile Flight](https://mlsanity.com/paper/2309.09865/) (2023)
- [Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning](https://mlsanity.com/paper/2503.01837/) (2025)
- [Part-Guided 3D RL for Sim2Real Articulated Object Manipulation](https://mlsanity.com/paper/2404.17302/) (2024)
- [Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision](https://mlsanity.com/paper/2506.06253/) (2025)
- [Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second](https://mlsanity.com/paper/2306.07552/) (2023)
- [Robotic-CLIP: Fine-tuning CLIP on Action Data for Robotic Applications](https://mlsanity.com/paper/2409.17727/) (2024)
- [Efficient Reinforcement Learning Through Adaptively Pretrained Visual Encoder](https://mlsanity.com/paper/2502.05555/) (2025)
- [Boosting Reinforcement Learning and Planning with Demonstrations: A Survey](https://mlsanity.com/paper/2303.13489/) (2023)
- [State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Grasping](https://mlsanity.com/paper/2309.11984/) (2023)
- [COMBO-Grasp: Learning Constraint-Based Manipulation for Bimanual Occluded Grasping](https://mlsanity.com/paper/2502.08054/) (2025)
- [Multi-Agent Transfer Learning via Temporal Contrastive Learning](https://mlsanity.com/paper/2406.01377/) (2024)
- [Reinforcement Learning for Robotic Insertion of Flexible Cables in Industrial Settings](https://mlsanity.com/paper/2509.13731/) (2025)
- [Scalable Dexterous Robot Learning with AR-based Remote Human-Robot Interactions](https://mlsanity.com/paper/2602.07341/) (2026)
- [Robust Scene Transfer for PointGoal Navigation via Privileged Sensor Guided Contrastive Learning](https://mlsanity.com/paper/2606.05506/) (2026)
- [Generalizable Robotic Insertion with World Models](https://mlsanity.com/paper/2609.28258/) (2026)

## Abstract (arXiv)

Recent advances in unsupervised representation learning significantly improved the sample efficiency of training Reinforcement Learning policies in simulated environments. However, similar gains have not yet been seen for real-robot reinforcement learning. In this work, we focus on enabling data-efficient real-robot learning from pixels. We present Contrastive Pre-training and Data Augmentation for Efficient Robotic Learning (CoDER), a method that utilizes data augmentation and unsupervised learning to achieve sample-efficient training of real-robot arm policies from sparse rewards. While contrastive pre-training, data augmentation, demonstrations, and reinforcement learning are alone insufficient for efficient learning, our main contribution is showing that the combination of these disparate techniques results in a simple yet data-efficient method. We show that, given only 10 demonstrations, a single robotic arm can learn sparse-reward manipulation policies from pixels, such as reaching, picking, moving, pulling a large object, flipping a switch, and opening a drawer in just 30 minutes of mean real-world training time. We include videos and code on the project website: https://sites.google.com/view/efficient-robotic-manipulation/home