mlsanityData to 7 Oct 2026

Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation

arXiv 1707.03374 ↗First posted 11 Jul 2017cs.LG cs.AI cs.CVcited by 167

Not on the map. Why?

Cited by 95 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Imitation learning is an effective approach for autonomous systems to acquire control policies when an explicit reward function is unavailable, using supervision provided as demonstrations from an expert, typically a human operator. However, standard imitation learning methods assume that the agent receives examples of observation-action tuples that could be provided, for instance, to a supervised learning algorithm. This stands in contrast to how humans and animals imitate: we observe another person performing some behavior and then figure out which actions will realize that behavior, compensating for changes in viewpoint, surroundings, object positions and types, and other factors. We term this kind of imitation learning "imitation-from-observation," and propose an imitation learning method based on video prediction with context translation and deep reinforcement learning. This lifts the assumption in imitation learning that the demonstration should consist of observations in the same environment configuration, and enables a variety of interesting applications, including learning robotic skills that involve tool use simply by observing videos of human tool use. Our experimental results show the effectiveness of our approach in learning a wide range of real-world robotic tasks modeled after common household chores from videos of a human demonstrator, including sweeping, ladling almonds, pushing objects as well as a number of tasks in simulation.

Key facts. Cited by 167 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 7; 2019: 14; 2020: 8; 2021: 23; 2022: 26; 2023: 28; 2024: 28; 2025: 21; 2026: 12.

167 papers.

Sort:

By area:

  1. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 678
  2. 2018Behavioral Cloning from Observationcited by 482
  3. 2018An Algorithmic Perspective on Imitation Learningcited by 455
  4. 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 338
  5. 2023Tool Learning with Foundation Modelscited by 302
  6. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 256
  7. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 248
  8. 2023MimicPlay: Long-Horizon Imitation Learning by Watching Human Playcited by 214
  9. 2021DexMV: Imitation Learning for Dexterous Manipulation from Human Videoscited by 194
  10. 2024HumanPlus: Humanoid Shadowing and Imitation from Humanscited by 164
  11. 2022Human-to-Robot Imitation in the Wildcited by 157
  12. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challengescited by 145
38 more
  1. 2024Flow as the Cross-Domain Manipulation Interfacecited by 126
  2. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 124
  3. 2021Learning Generalizable Robotic Reward Functions from "In-The-Wild" Human Videoscited by 116
  4. 2019Imitation Learning from Imperfect Demonstrationcited by 112
  5. 2022Reinforcement Learning with Action-Free Pre-Training from Videoscited by 107
  6. 2021XIRL: Cross-embodiment Inverse Reinforcement Learningcited by 101
  7. 2019Recent Advances in Imitation Learning from Observationcited by 92
  8. 2020State-Only Imitation Learning for Dexterous Manipulationcited by 90
  9. 2021Learning by Watching: Physical Imitation of Manipulation Skills from Human Videoscited by 87
  10. 2022DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Videocited by 83
  11. 2022From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperationcited by 79
  12. 2019Provably Efficient Imitation Learning from Observation Alonecited by 78
  13. 2023Video Prediction Models as Rewards for Reinforcement Learningcited by 76
  14. 2023XSkill: Cross Embodiment Skill Discoverycited by 74
  15. 2019State Alignment-based Imitation Learningcited by 73
  16. 2021Off-Policy Imitation Learning from Observationscited by 70
  17. 2025Large Video Planner Enables Generalizable Robot Controlcited by 67
  18. 2021Imitation Learning: Progress, Taxonomies and Challengescited by 56
  19. 2020Model-Based Inverse Reinforcement Learning from Visual Demonstrationscited by 52
  20. 2020Deep Imitation Learning for Bimanual Robotic Manipulationcited by 49
  21. 2021Cross-Domain Imitation Learning via Optimal Transportcited by 49
  22. 2024Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformerscited by 47
  23. 2019Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreementcited by 46
  24. 2023Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignmentcited by 46
  25. 2024Vision-based Manipulation from Single Human Video with Open-World Object Graphscited by 46
  26. 2023Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learningcited by 45
  27. 2021Cross-domain Imitation from Observationscited by 42
  28. 2025VideoWorld: Exploring Knowledge Learning from Unlabeled Videoscited by 42
  29. 2025CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrationscited by 39
  30. 2025Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrationscited by 33
  31. 2018One-Shot Hierarchical Imitation Learning of Compound Visuomotor Taskscited by 32
  32. 2021VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigationcited by 27
  33. 2022Frame-wise Action Representations for Long Videos via Sequence Contrastive Learningcited by 27
  34. 2022K-VIL: Keypoints-based Visual Imitation Learningcited by 27
  35. 2022Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectoriescited by 27
  36. 2018Inverse reinforcement learning for video gamescited by 26
  37. 2018Learning from Demonstration in the Wildcited by 25
  38. 2019Imitation Learning from Video by Leveraging Proprioceptioncited by 23

50 most cited of 167 All 167 (JSON)