mlsanityData to 7 Oct 2026

Generative Adversarial Imitation from Observation

arXiv 1807.06158 ↗First posted 17 Jul 2018cs.LG cs.AI stat.MLcited by 183

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

Abstract (arXiv)

Imitation from observation (IfO) is the problem of learning directly from state-only demonstrations without having access to the demonstrator's actions. The lack of action information both distinguishes IfO from most of the literature in imitation learning, and also sets it apart as a method that may enable agents to learn from a large set of previously inapplicable resources such as internet videos. In this paper, we propose both a general framework for IfO approaches and also a new IfO approach based on generative adversarial networks called generative adversarial imitation from observation (GAIfO). We conduct experiments in two different settings: (1) when demonstrations consist of low-dimensional, manually-defined state features, and (2) when demonstrations consist of high-dimensional, raw visual data. We demonstrate that our approach performs comparably to classical imitation learning approaches (which have access to the demonstrator's actions) and significantly outperforms existing imitation from observation methods in high-dimensional simulation environments.

Key facts. Cited by 183 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. First posted on arXiv 17 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 2; 2019: 9; 2020: 6; 2021: 25; 2022: 34; 2023: 41; 2024: 30; 2025: 24; 2026: 12.

183 papers.

Sort:

By area:

  1. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 256
  2. 2018Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learningcited by 203
  3. 2021DexMV: Imitation Learning for Dexterous Manipulation from Human Videoscited by 194
  4. 2023Learning to Act from Actionless Videos through Dense Correspondencescited by 159
  5. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 151
  6. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challengescited by 145
  7. 2019Imitation Learning as f-Divergence Minimizationcited by 121
  8. 2023Learning to Act without Actionscited by 116
  9. 2022Reinforcement Learning with Action-Free Pre-Training from Videoscited by 107
  10. 2021XIRL: Cross-embodiment Inverse Reinforcement Learningcited by 101
  11. 2019Recent Advances in Imitation Learning from Observationcited by 92
  12. 2023CALM: Conditional Adversarial Latent Models for Directable Virtual Characterscited by 91
38 more
  1. 2020State-Only Imitation Learning for Dexterous Manipulationcited by 90
  2. 2022From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperationcited by 79
  3. 2023Video Prediction Models as Rewards for Reinforcement Learningcited by 76
  4. 2023Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrationscited by 74
  5. 2019State Alignment-based Imitation Learningcited by 73
  6. 2021Off-Policy Imitation Learning from Observationscited by 70
  7. 2022How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via f-Advantage Regressioncited by 65
  8. 2022Watch and Match: Supercharging Imitation with Regularized Optimal Transportcited by 64
  9. 2023Reinforcement Learning from Passive Data via Latent Intentionscited by 64
  10. 2021Imitation Learning: Progress, Taxonomies and Challengescited by 56
  11. 2023Diffusion Reward: Learning Rewards via Conditional Video Diffusioncited by 56
  12. 2023Zero-Shot Robot Manipulation from Passive Human Videoscited by 49
  13. 2019Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreementcited by 46
  14. 2022Learning Generalizable Dexterous Manipulation from Human Grasp Affordancecited by 46
  15. 2024Vision-based Manipulation from Single Human Video with Open-World Object Graphscited by 46
  16. 2022Graph Inverse Reinforcement Learning from Diverse Videoscited by 45
  17. 2021MobILE: Model-Based Imitation Learning From Observation Alonecited by 44
  18. 2022Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matchingcited by 43
  19. 2022Hierarchical Model-Based Imitation Learning for Planning in Autonomous Drivingcited by 43
  20. 2022Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guaranteescited by 42
  21. 2021Adversarial Intrinsic Motivation for Reinforcement Learningcited by 40
  22. 2024Towards Generalist Robot Learning from Internet Video: A Surveycited by 40
  23. 2023Diffusion Model-Augmented Behavioral Cloningcited by 37
  24. 2024Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrationscited by 35
  25. 2020Robust Inverse Reinforcement Learning under Transition Dynamics Mismatchcited by 33
  26. 2023Prompt, Plan, Perform: LLM-based Humanoid Control via Quantized Imitation Learningcited by 31
  27. 2023Robotic Offline RL from Internet Videos via Value-Function Pre-Trainingcited by 31
  28. 2023LocoMuJoCo: A Comprehensive Imitation Learning Benchmark for Locomotioncited by 31
  29. 2023Cross-Domain Policy Adaptation via Value-Guided Data Filteringcited by 30
  30. 2023LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learningcited by 28
  31. 2021VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigationcited by 27
  32. 2021StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learningcited by 27
  33. 2022K-VIL: Keypoints-based Visual Imitation Learningcited by 27
  34. 2022Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectoriescited by 27
  35. 2021Learning from Imperfect Demonstrations from Agents with Varying Dynamicscited by 26
  36. 2022Robust Imitation Learning against Variations in Environment Dynamicscited by 26
  37. 2019Imitation Learning from Video by Leveraging Proprioceptioncited by 23
  38. 2022LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimationcited by 22

50 most cited of 183 All 183 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2018Behavioral Cloning from Observation
  2. 2018Sample-Efficient Imitation Learning via Generative Adversarial Nets
  3. 2023Sample-efficient Adversarial Imitation Learning
  4. 2021Domain-Robust Visual Imitation Learning with Mutual Information Constraints
  5. 2026Generative adversarial imitation learning for robot swarms: Learning from human demonstrations and trained policies
  6. 2021Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency
  7. 2019Adversarial Imitation Learning from Incomplete Demonstrations
  8. 2023SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models