mlsanityData to 14 Oct 2026

Recent Advances in Imitation Learning from Observation

arXiv 1905.13566 ↗First posted 30 May 2019cs.RO cs.AI cs.LGcited by 93

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

Abstract (arXiv)

Imitation learning is the process by which one agent tries to learn how to perform a certain task using information generated by another, often more-expert agent performing that same task. Conventionally, the imitator has access to both state and action information generated by an expert performing the task (e.g., the expert may provide a kinesthetic demonstration of object placement using a robotic arm). However, requiring the action information prevents imitation learning from a large number of existing valuable learning resources such as online videos of humans performing tasks. To overcome this issue, the specific problem of imitation from observation (IfO) has recently garnered a great deal of attention, in which the imitator only has access to the state information (e.g., video frames) generated by the expert. In this paper, we provide a literature review of methods developed for IfO, and then point out some open research problems and potential future work.

Key facts. Cited by 93 papers in the map (data through 14 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 29 of its 75 references that are in the map. First posted on arXiv 30 May 2019.

Builds on

29 of 75 references.

Closest ancestors · 7

Same direction, newest first

  1. 2019Provably Efficient Imitation Learning from Observation Alone27 May
  2. 2019Imitation Learning from Video by Leveraging Proprioception22 May
  3. 2019Hybrid Reinforcement Learning with Expert State Sequences11 Mar
  4. 2018An Algorithmic Perspective on Imitation Learning16 Nov
  5. 2018Generative Adversarial Imitation from Observation17 Jul
  6. 2018Imitating Latent Policies from Observation21 May
  7. 2018Behavioral Cloning from Observation4 May

Other references · 22

  1. 2016Generative Adversarial Imitation Learningcited by 1,597
  2. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  3. 2016End to End Learning for Self-Driving Carscited by 1,009
  4. 2018Deep Visual Domain Adaptation: A Surveycited by 635
  5. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 490
  6. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 459
  7. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 406
  8. 2017One-Shot Visual Imitation Learning via Meta-Learningcited by 228
  9. 2017Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translationcited by 167
  10. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 126
  11. 2018Zero-Shot Visual Imitationcited by 117
  12. 2017Third-Person Imitation Learningcited by 103
10 more
  1. 2018Playing hard exploration games by watching YouTubecited by 99
  2. 2017Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulationcited by 90
  3. 2017Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learningcited by 85
  4. 2017Learning human behaviors from motion capture by adversarial imitationcited by 77
  5. 2017OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learningcited by 40
  6. 2018Learning Actionable Representations from Visual Observationscited by 35
  7. 2016Learning Transferable Policies for Monocular Reactive MAV Controlcited by 18
  8. 20193D Human Pose Machines with Self-supervised Learningcited by 17
  9. 2018One-Shot Learning of Multi-Step Tasks from Observation via Activity Localization in Auxiliary Videocited by 16
  10. 2018Internal Model from Observations for Reward Shapingcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 2; 2020: 5; 2021: 7; 2022: 19; 2023: 21; 2024: 19; 2025: 14; 2026: 6.

93 papers.

Sort:

By area:

  1. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 478
  2. 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 345
  3. 2023Learning to Act from Actionless Videos through Dense Correspondencescited by 164
  4. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challengescited by 148
  5. 2023Learning to Act without Actionscited by 121
  6. 2022DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Videocited by 89
  7. 2023Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrationscited by 75
  8. 2021Off-Policy Imitation Learning from Observationscited by 70
  9. 2022Watch and Match: Supercharging Imitation with Regularized Optimal Transportcited by 67
  10. 2021Imitation Learning: Progress, Taxonomies and Challengescited by 58
  11. 2025Latent Action Learning Requires Supervision in the Presence of Distractorscited by 44
  12. 2024Towards Generalist Robot Learning from Internet Video: A Surveycited by 40
38 more
  1. 2023World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challengescited by 36
  2. 2025Planning with Reasoning using Vision Language World Modelcited by 36
  3. 2023See to Touch: Learning Tactile Dexterity through Visual Incentivescited by 35
  4. 2024Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrationscited by 35
  5. 2023Hyper-Decision Transformer for Efficient Online Policy Adaptationcited by 33
  6. 2024Rank2Reward: Learning Shaped Reward Functions from Passive Videocited by 32
  7. 2021VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigationcited by 31
  8. 2020Imitation Learning with Sinkhorn Distancescited by 30
  9. 2023LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learningcited by 29
  10. 2022Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectoriescited by 28
  11. 2022Deep Interactive Motion Prediction and Planning: Playing Games with Motion Prediction Modelscited by 27
  12. 2024VideoAgent: Self-Improving Video Generationcited by 25
  13. 2021Domain-Robust Visual Imitation Learning with Mutual Information Constraintscited by 20
  14. 2022A Ranking Game for Imitation Learningcited by 18
  15. 2022SelfD: Self-Learning Large-Scale Driving Policies From the Webcited by 18
  16. 2023MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observationscited by 18
  17. 2024Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitationcited by 17
  18. 2024A Survey of Imitation Learning Methods, Environments and Metricscited by 16
  19. 2024P3-PO: Prescriptive Point Priors for Visuo-Spatial Generalization of Robot Policiescited by 16
  20. 2024SEABO: A Simple Search-Based Method for Offline Imitation Learningcited by 14
  21. 2021Imitation by Predicting Observationscited by 13
  22. 2021Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Taskscited by 13
  23. 2022Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy Optimizationcited by 12
  24. 2025Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learningcited by 12
  25. 2020Learning Coupled Policies for Simultaneous Machine Translation using Imitation Learningcited by 10
  26. 2022Adversarial Imitation Learning from Video using a State Observercited by 10
  27. 2022Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learningcited by 10
  28. 2023Aligning Step-by-Step Instructional Diagrams to Video Demonstrationscited by 10
  29. 2023Imitation Learning from Observation with Automatic Discount Schedulingcited by 10
  30. 2024Towards Principled Representation Learning from Videos for Reinforcement Learningcited by 10
  31. 2024Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matchingcited by 10
  32. 2022Learning Robust Real-Time Cultural Transmission without Human Datacited by 9
  33. 2024PianoMime: Learning a Generalist, Dexterous Piano Player from Internet Demonstrationscited by 9
  34. 2022Planning with RL and episodic-memory behavioral priorscited by 8
  35. 2023Learning Robot Manipulation from Cross-Morphology Demonstrationcited by 8
  36. 2020Domain-Adversarial and Conditional State Space Model for Imitation Learningcited by 7
  37. 2019Sample-efficient Adversarial Imitation Learning from Observationcited by 6
  38. 2022Imitation Learning by State-Only Distribution Matchingcited by 6

50 most cited of 93 All 93 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Value from Observations: Towards Large-Scale Imitation Learning via Self-Improvement
  2. 2022Imitation Learning from Observations under Transition Model Disparity
  3. 2024Explorative Imitation Learning: A Path Signature Approach for Continuous Environments
  4. 2022Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction
  5. 2019Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement
  6. 2019To Follow or not to Follow: Selective Imitation Learning from Observations
  7. 2024Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained World Models
  8. 2019State Alignment-based Imitation Learning