mlsanityData to 7 Oct 2026

Imitation Learning from Video by Leveraging Proprioception

arXiv 1905.09335 ↗First posted 22 May 2019cs.LG stat.MLcited by 23

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

Classically, imitation learning algorithms have been developed for idealized situations, e.g., the demonstrations are often required to be collected in the exact same environment and usually include the demonstrator's actions. Recently, however, the research community has begun to address some of these shortcomings by offering algorithmic solutions that enable imitation learning from observation (IfO), e.g., learning to perform a task from visual demonstrations that may be in a different environment and do not include actions. Motivated by the fact that agents often also have access to their own internal states (i.e., proprioception), we propose and study an IfO algorithm that leverages this information in the policy learning process. The proposed architecture learns policies over proprioceptive state representations and compares the resulting trajectories visually to the demonstration data. We experimentally test the proposed technique on several MuJoCo domains and show that it outperforms other imitation from observation algorithms by a large margin.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 19 of its 56 references that are in the map. First posted on arXiv 22 May 2019.

Builds on

19 of 56 references.

Closest ancestors · 5

Same direction, newest first

  1. 2018An Algorithmic Perspective on Imitation Learning16 Nov
  2. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning9 Sep
  3. 2018Generative Adversarial Imitation from Observation17 Jul
  4. 2018Imitating Latent Policies from Observation21 May
  5. 2018Behavioral Cloning from Observation4 May

Other references · 14

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  4. 2015Trust Region Policy Optimizationcited by 2,503
  5. 2016Generative Adversarial Imitation Learningcited by 1,576
  6. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  7. 2017Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translationcited by 167
  8. 2017Third-Person Imitation Learningcited by 103
  9. 2018Playing hard exploration games by watching YouTubecited by 98
  10. 2017Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learningcited by 84
  11. 2017Learning human behaviors from motion capture by adversarial imitationcited by 75
  12. 2018Adversarial Imitation via Variational Inverse Reinforcement Learningcited by 36
2 more
  1. 2016Learning Transferable Policies for Monocular Reactive MAV Controlcited by 18
  2. 2018One-Shot Learning of Multi-Step Tasks from Observation via Activity Localization in Auxiliary Videocited by 16

Built on by

Cited by year

Citing papers per year: 2019: 3; 2020: 0; 2021: 4; 2022: 4; 2023: 4; 2024: 5; 2025: 3.

23 papers.

Sort:

By area:

  1. 2019Recent Advances in Imitation Learning from Observationcited by 92
  2. 2021Imitation Learning: Progress, Taxonomies and Challengescited by 56
  3. 2019Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreementcited by 46
  4. 2024Vision-based Manipulation from Single Human Video with Open-World Object Graphscited by 46
  5. 2022Visuo-Tactile Transformers for Manipulationcited by 43
  6. 2021VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigationcited by 27
  7. 2022K-VIL: Keypoints-based Visual Imitation Learningcited by 27
  8. 2024A Survey of Imitation Learning Methods, Environments and Metricscited by 16
  9. 2025Do You Need Proprioceptive States in Visuomotor Policies?cited by 16
  10. 2024Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitationcited by 15
  11. 2021Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Taskscited by 13
  12. 2022Adversarial Imitation Learning from Video using a State Observercited by 10
11 more
  1. 2023SeMAIL: Eliminating Distractors in Visual Imitation via Separated Modelscited by 10
  2. 2022Learning Value Functions from Undirected State-only Experiencecited by 8
  3. 2024Pre-trained Visual Dynamics Representations for Efficient Policy Learningcited by 8
  4. 2019Sample-efficient Adversarial Imitation Learning from Observationcited by 6
  5. 2023What You Say Is What You Show: Visual Narration Detection in Instructional Videoscited by 5
  6. 2021DEALIO: Data-Efficient Adversarial Learning for Imitation from Observationcited by 4
  7. 2024NOLO: Navigate Only Look Oncecited by 3
  8. 2023Genetic Imitation Learning by Reward Extrapolationcited by 1
  9. 2023Imitation from Observation With Bootstrapped Contrastive Learningcited by 1
  10. 2025Improving Robustness to Out-of-Distribution States in Imitation Learning via Deep Koopman-Boosted Diffusion Policycited by 1
  11. 2025GIFT: Geometry-Induced Functional Transfer for Category-level Object Manipulationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Value from Observations: Towards Large-Scale Imitation Learning via Self-Improvement
  2. 2025Learning from Observation: A Survey of Recent Advances
  3. 2022Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction
  4. 2024A Dual Approach to Imitation Learning from Observations with Offline Datasets
  5. 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances
  6. 2023Adversarial Imitation Learning from Visual Observations using Latent Information
  7. 2024Explorative Imitation Learning: A Path Signature Approach for Continuous Environments
  8. 2022Imitation Learning from Observations under Transition Model Disparity