# Self-Supervised Disentangled Representation Learning for Third-Person Imitation Learning

arXiv: https://arxiv.org/abs/2108.01069 · HTML: https://mlsanity.com/paper/2108.01069/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 32 of its 41 references that are in the map.
- First posted on arXiv 2 Aug 2021.

## Placed in

- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 30 of 32)

- [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)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [MineRL: A Large-Scale Dataset of Minecraft Demonstrations](https://mlsanity.com/paper/1907.13440/) (2019)
- [Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation](https://mlsanity.com/paper/1707.03374/) (2017)
- [Isolating Sources of Disentanglement in Variational Autoencoders](https://mlsanity.com/paper/1802.04942/) (2018)
- [Unsupervised Learning of Disentangled Representations from Video](https://mlsanity.com/paper/1705.10915/) (2017)
- [Domain Agnostic Learning with Disentangled Representations](https://mlsanity.com/paper/1904.12347/) (2019)
- [Third-Person Imitation Learning](https://mlsanity.com/paper/1703.01703/) (2017)
- [Imitating Latent Policies from Observation](https://mlsanity.com/paper/1805.07914/) (2018)
- [Playing hard exploration games by watching YouTube](https://mlsanity.com/paper/1805.11592/) (2018)
- [Neural Face Editing with Intrinsic Image Disentangling](https://mlsanity.com/paper/1704.04131/) (2017)
- [Gait Recognition via Disentangled Representation Learning](https://mlsanity.com/paper/1904.04925/) (2019)
- [Disentangled Representation Learning for 3D Face Shape](https://mlsanity.com/paper/1902.09887/) (2019)
- [Task-Relevant Adversarial Imitation Learning](https://mlsanity.com/paper/1910.01077/) (2019)
- [Contextual Imagined Goals for Self-Supervised Robotic Learning](https://mlsanity.com/paper/1910.11670/) (2019)
- [Learning Actionable Representations from Visual Observations](https://mlsanity.com/paper/1808.00928/) (2018)

## Built on by (most cited first, 23 of 23)

- [Perceptual Grouping in Contrastive Vision-Language Models](https://mlsanity.com/paper/2210.09996/) (2022)
- [Theia: Distilling Diverse Vision Foundation Models for Robot Learning](https://mlsanity.com/paper/2407.20179/) (2024)
- [Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning](https://mlsanity.com/paper/2307.01849/) (2023)
- [Towards Generalist Robot Learning from Internet Video: A Survey](https://mlsanity.com/paper/2404.19664/) (2024)
- [StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning](https://mlsanity.com/paper/2110.06206/) (2021)
- [Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?](https://mlsanity.com/paper/2206.05266/) (2022)
- [EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs](https://mlsanity.com/paper/2507.18342/) (2025)
- [Unsupervised Representation Learning in Deep Reinforcement Learning: A Review](https://mlsanity.com/paper/2208.14226/) (2022)
- [MoVie: Visual Model-Based Policy Adaptation for View Generalization](https://mlsanity.com/paper/2307.00972/) (2023)
- [A Survey of Imitation Learning Methods, Environments and Metrics](https://mlsanity.com/paper/2404.19456/) (2024)
- [Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space](https://mlsanity.com/paper/2206.11895/) (2022)
- [A Survey of Demonstration Learning](https://mlsanity.com/paper/2303.11191/) (2023)
- [Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras](https://mlsanity.com/paper/2404.14064/) (2024)
- [Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision](https://mlsanity.com/paper/2506.06253/) (2025)
- [Visual-Policy Learning through Multi-Camera View to Single-Camera View Knowledge Distillation for Robot Manipulation Tasks](https://mlsanity.com/paper/2303.07026/) (2023)
- [ProtoX: Explaining a Reinforcement Learning Agent via Prototyping](https://mlsanity.com/paper/2211.03162/) (2022)
- [Contrastive Learning from Demonstrations](https://mlsanity.com/paper/2201.12813/) (2022)
- [Neural Neural Textures Make Sim2Real Consistent](https://mlsanity.com/paper/2206.13500/) (2022)
- [Active Third-Person Imitation Learning](https://mlsanity.com/paper/2312.16365/) (2023)
- [SENSOR: Imitate Third-Person Expert's Behaviors via Active Sensoring](https://mlsanity.com/paper/2404.03386/) (2024)
- [Active Vision Reinforcement Learning under Limited Visual Observability](https://mlsanity.com/paper/2306.00975/) (2023)
- [Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers](https://mlsanity.com/paper/2306.09331/) (2023)
- [Mirror Learning](https://mlsanity.com/paper/2607.28737/) (2026)

## Abstract (arXiv)

Humans learn to imitate by observing others. However, robot imitation learning generally requires expert demonstrations in the first-person view (FPV). Collecting such FPV videos for every robot could be very expensive. Third-person imitation learning (TPIL) is the concept of learning action policies by observing other agents in a third-person view (TPV), similar to what humans do. This ultimately allows utilizing human and robot demonstration videos in TPV from many different data sources, for the policy learning. In this paper, we present a TPIL approach for robot tasks with egomotion. Although many robot tasks with ground/aerial mobility often involve actions with camera egomotion, study on TPIL for such tasks has been limited. Here, FPV and TPV observations are visually very different; FPV shows egomotion while the agent appearance is only observable in TPV. To enable better state learning for TPIL, we propose our disentangled representation learning method. We use a dual auto-encoder structure plus representation permutation loss and time-contrastive loss to ensure the state and viewpoint representations are well disentangled. Our experiments show the effectiveness of our approach.