# Evaluating Vision Transformer Methods for Deep Reinforcement Learning from Pixels

arXiv: https://arxiv.org/abs/2204.04905 · HTML: https://mlsanity.com/paper/2204.04905/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 48 references that are in the map.
- First posted on arXiv 11 Apr 2022.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [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)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [Data-Efficient Image Recognition with Contrastive Predictive Coding](https://mlsanity.com/paper/1905.09272/) (2019)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)
- [Reinforcement Learning with Augmented Data](https://mlsanity.com/paper/2004.14990/) (2020)
- [dm_control: Software and Tasks for Continuous Control](https://mlsanity.com/paper/2006.12983/) (2020)
- [Data-Efficient Reinforcement Learning with Self-Predictive Representations](https://mlsanity.com/paper/2007.05929/) (2020)

## Built on by (most cited first, 13 of 13)

- [Foundation Models for Decision Making: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2303.04129/) (2023)
- [A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond](https://mlsanity.com/paper/2208.00173/) (2022)
- [A Survey on Transformers in Reinforcement Learning](https://mlsanity.com/paper/2301.03044/) (2023)
- [Vision Transformers for End-to-End Vision-Based Quadrotor Obstacle Avoidance](https://mlsanity.com/paper/2405.10391/) (2024)
- [Transformers in Reinforcement Learning: A Survey](https://mlsanity.com/paper/2307.05979/) (2023)
- [MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning](https://mlsanity.com/paper/2312.15339/) (2023)
- [Transformer in Transformer as Backbone for Deep Reinforcement Learning](https://mlsanity.com/paper/2212.14538/) (2022)
- [Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement Learning](https://mlsanity.com/paper/2209.10901/) (2022)
- [A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functions](https://mlsanity.com/paper/2508.09128/) (2025)
- [Deep Reinforcement Learning with Swin Transformers](https://mlsanity.com/paper/2206.15269/) (2022)
- [Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment](https://mlsanity.com/paper/2407.19380/) (2024)
- [Unsupervised Salient Patch Selection for Data-Efficient Reinforcement Learning](https://mlsanity.com/paper/2402.03329/) (2024)
- [MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement Learning in Unstructured Autonomous Driving](https://mlsanity.com/paper/2609.20747/) (2026)

## Abstract (arXiv)

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.