# On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline

arXiv: https://arxiv.org/abs/2212.05749 · HTML: https://mlsanity.com/paper/2212.05749/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 58 references that are in the map.
- First posted on arXiv 12 Dec 2022.

## Builds on (most cited first, 30 of 40)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [Reinforcement Learning with Augmented Data](https://mlsanity.com/paper/2004.14990/) (2020)
- [Temporal Difference Learning for Model Predictive Control](https://mlsanity.com/paper/2203.04955/) (2022)
- [Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning](https://mlsanity.com/paper/2107.09645/) (2021)
- [Data-Efficient Reinforcement Learning with Self-Predictive Representations](https://mlsanity.com/paper/2007.05929/) (2020)
- [Improving Sample Efficiency in Model-Free Reinforcement Learning from Images](https://mlsanity.com/paper/1910.01741/) (2019)
- [When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations](https://mlsanity.com/paper/2106.01548/) (2021)
- [Masked Visual Pre-training for Motor Control](https://mlsanity.com/paper/2203.06173/) (2022)
- [Asymmetric Actor Critic for Image-Based Robot Learning](https://mlsanity.com/paper/1710.06542/) (2017)
- [The Unsurprising Effectiveness of Pre-Trained Vision Models for Control](https://mlsanity.com/paper/2203.03580/) (2022)

## Built on by (most cited first, 30 of 56)

- [MimicPlay: Long-Horizon Imitation Learning by Watching Human Play](https://mlsanity.com/paper/2302.12422/) (2023)
- [Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?](https://mlsanity.com/paper/2303.18240/) (2023)
- [LIV: Language-Image Representations and Rewards for Robotic Control](https://mlsanity.com/paper/2306.00958/) (2023)
- [HumanPlus: Humanoid Shadowing and Imitation from Humans](https://mlsanity.com/paper/2406.10454/) (2024)
- [RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking](https://mlsanity.com/paper/2309.01918/) (2023)
- [Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning](https://mlsanity.com/paper/2311.17842/) (2023)
- [Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation](https://mlsanity.com/paper/2409.16283/) (2024)
- [3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations](https://mlsanity.com/paper/2403.03954/) (2024)
- [Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis](https://mlsanity.com/paper/2312.08782/) (2023)
- [GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields](https://mlsanity.com/paper/2308.16891/) (2023)
- [General Flow as Foundation Affordance for Scalable Robot Learning](https://mlsanity.com/paper/2401.11439/) (2024)
- [Imitation Bootstrapped Reinforcement Learning](https://mlsanity.com/paper/2311.02198/) (2023)
- [Learning Generalizable Manipulation Policies with Object-Centric 3D Representations](https://mlsanity.com/paper/2310.14386/) (2023)
- [Diffusion Reward: Learning Rewards via Conditional Video Diffusion](https://mlsanity.com/paper/2312.14134/) (2023)
- [TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models](https://mlsanity.com/paper/2310.05905/) (2023)
- [Generalizable Humanoid Manipulation with 3D Diffusion Policies](https://mlsanity.com/paper/2410.10803/) (2024)
- [Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning](https://mlsanity.com/paper/2402.02500/) (2024)
- [An Unbiased Look at Datasets for Visuo-Motor Pre-Training](https://mlsanity.com/paper/2310.09289/) (2023)
- [Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning](https://mlsanity.com/paper/2407.15815/) (2024)
- [Learning Manipulation by Predicting Interaction](https://mlsanity.com/paper/2406.00439/) (2024)
- [Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation](https://mlsanity.com/paper/2304.06600/) (2023)
- [Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages](https://mlsanity.com/paper/2310.07418/) (2023)
- [Hierarchical World Models as Visual Whole-Body Humanoid Controllers](https://mlsanity.com/paper/2405.18418/) (2024)
- [SpawnNet: Learning Generalizable Visuomotor Skills from Pre-trained Networks](https://mlsanity.com/paper/2307.03567/) (2023)
- [Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning](https://mlsanity.com/paper/2310.20587/) (2023)
- [Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets](https://mlsanity.com/paper/2410.22325/) (2024)
- [For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equal](https://mlsanity.com/paper/2304.04591/) (2023)
- [Chain-of-Thought Predictive Control](https://mlsanity.com/paper/2304.00776/) (2023)
- [SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation](https://mlsanity.com/paper/2405.19586/) (2024)
- [Semantically Controllable Augmentations for Generalizable Robot Learning](https://mlsanity.com/paper/2409.00951/) (2024)

## Abstract (arXiv)

In this paper, we examine the effectiveness of pre-training for visuo-motor control tasks. We revisit a simple Learning-from-Scratch (LfS) baseline that incorporates data augmentation and a shallow ConvNet, and find that this baseline is surprisingly competitive with recent approaches (PVR, MVP, R3M) that leverage frozen visual representations trained on large-scale vision datasets -- across a variety of algorithms, task domains, and metrics in simulation and on a real robot. Our results demonstrate that these methods are hindered by a significant domain gap between the pre-training datasets and current benchmarks for visuo-motor control, which is alleviated by finetuning. Based on our findings, we provide recommendations for future research in pre-training for control and hope that our simple yet strong baseline will aid in accurately benchmarking progress in this area.