# Pre-trained Visual Dynamics Representations for Efficient Policy Learning

arXiv: https://arxiv.org/abs/2411.03169 · HTML: https://mlsanity.com/paper/2411.03169/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 81 of its 94 references that are in the map.
- First posted on arXiv 5 Nov 2024.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 30 of 81)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation](https://mlsanity.com/paper/2209.05451/) (2022)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [Phenaki: Variable Length Video Generation From Open Domain Textual Description](https://mlsanity.com/paper/2210.02399/) (2022)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training](https://mlsanity.com/paper/2210.00030/) (2022)
- [Planning to Explore via Self-Supervised World Models](https://mlsanity.com/paper/2005.05960/) (2020)
- [Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation](https://mlsanity.com/paper/2312.13139/) (2023)

## Built on by (most cited first, 8 of 8)

- [Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild](https://mlsanity.com/paper/2602.21736/) (2026)
- [MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation](https://mlsanity.com/paper/2505.16602/) (2025)
- [STORM: Search-Guided Generative World Models for Robotic Manipulation](https://mlsanity.com/paper/2512.18477/) (2025)
- [Towards Empowerment Gain through Causal Structure Learning in Model-Based RL](https://mlsanity.com/paper/2502.10077/) (2025)
- [Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations](https://mlsanity.com/paper/2512.21586/) (2025)
- [Emerging Extrinsic Dexterity in Cluttered Scenes via Dynamics-aware Policy Learning](https://mlsanity.com/paper/2603.09882/) (2026)
- [Action-Free Offline-to-Online RL via Discretised State Policies](https://mlsanity.com/paper/2602.00629/) (2026)
- [GoStop: Reinforcement Learning for Adaptive Temporal Aggregation in Event-Based Feature Tracking](https://mlsanity.com/paper/2607.15699/) (2026)

## Abstract (arXiv)

Pre-training for Reinforcement Learning (RL) with purely video data is a valuable yet challenging problem. Although in-the-wild videos are readily available and inhere a vast amount of prior world knowledge, the absence of action annotations and the common domain gap with downstream tasks hinder utilizing videos for RL pre-training. To address the challenge of pre-training with videos, we propose Pre-trained Visual Dynamics Representations (PVDR) to bridge the domain gap between videos and downstream tasks for efficient policy learning. By adopting video prediction as a pre-training task, we use a Transformer-based Conditional Variational Autoencoder (CVAE) to learn visual dynamics representations. The pre-trained visual dynamics representations capture the visual dynamics prior knowledge in the videos. This abstract prior knowledge can be readily adapted to downstream tasks and aligned with executable actions through online adaptation. We conduct experiments on a series of robotics visual control tasks and verify that PVDR is an effective form for pre-training with videos to promote policy learning.