mlsanityData to 14 Oct 2026

Imitating Latent Policies from Observation

arXiv 1805.07914 ↗First posted 21 May 2018cs.LG stat.MLcited by 101

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

Abstract (arXiv)

In this paper, we describe a novel approach to imitation learning that infers latent policies directly from state observations. We introduce a method that characterizes the causal effects of latent actions on observations while simultaneously predicting their likelihood. We then outline an action alignment procedure that leverages a small amount of environment interactions to determine a mapping between the latent and real-world actions. We show that this corrected labeling can be used for imitating the observed behavior, even though no expert actions are given. We evaluate our approach within classic control environments and a platform game and demonstrate that it performs better than standard approaches. Code for this work is available at https://github.com/ashedwards/ILPO.

Key facts. Cited by 101 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. First posted on arXiv 21 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 4; 2020: 5; 2021: 10; 2022: 19; 2023: 8; 2024: 16; 2025: 16; 2026: 23.

101 papers.

Sort:

By area:

  1. 2024Genie: Generative Interactive Environmentscited by 747
  2. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 478
  3. 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 345
  4. 2024Latent Action Pretraining from Videoscited by 321
  5. 2025Motus: A Unified Latent Action World Modelcited by 251
  6. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challengescited by 148
  7. 2020Primal Wasserstein Imitation Learningcited by 121
  8. 2023Learning to Act without Actionscited by 121
  9. 2026VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Modelcited by 118
  10. 2025AdaWorld: Learning Adaptable World Models with Latent Actionscited by 114
  11. 2022Reinforcement Learning with Action-Free Pre-Training from Videoscited by 108
  12. 2021XIRL: Cross-embodiment Inverse Reinforcement Learningcited by 107
38 more
  1. 2019Recent Advances in Imitation Learning from Observationcited by 93
  2. 2020State-Only Imitation Learning for Dexterous Manipulationcited by 91
  3. 2024Video as the New Language for Real-World Decision Makingcited by 87
  4. 2019Provably Efficient Imitation Learning from Observation Alonecited by 78
  5. 2019State Alignment-based Imitation Learningcited by 73
  6. 2021Off-Policy Imitation Learning from Observationscited by 70
  7. 2021Imitation Learning: Progress, Taxonomies and Challengescited by 58
  8. 2026Learning Latent Action World Models In The Wildcited by 47
  9. 2021MobILE: Model-Based Imitation Learning From Observation Alonecited by 44
  10. 2024DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Controlcited by 44
  11. 2025Latent Action Learning Requires Supervision in the Presence of Distractorscited by 44
  12. 2020Provable Representation Learning for Imitation Learning via Bi-level Optimizationcited by 41
  13. 2024Towards Generalist Robot Learning from Internet Video: A Surveycited by 40
  14. 2025What Do Latent Action Models Actually Learn?cited by 32
  15. 2022Deep Interactive Motion Prediction and Planning: Playing Games with Motion Prediction Modelscited by 27
  16. 2026NitroGen: An Open Foundation Model for Generalist Gaming Agentscited by 27
  17. 2025Latent Diffusion Planning for Imitation Learningcited by 26
  18. 2019Imitation Learning from Video by Leveraging Proprioceptioncited by 23
  19. 2021Self-Supervised Disentangled Representation Learning for Third-Person Imitation Learningcited by 23
  20. 2023Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Modelscited by 21
  21. 2022MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENerationcited by 20
  22. 2022A Ranking Game for Imitation Learningcited by 18
  23. 2022Discriminator-Guided Model-Based Offline Imitation Learningcited by 17
  24. 2024From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systemscited by 17
  25. 2022Dungeons and Data: A Large-Scale NetHack Datasetcited by 16
  26. 2024A Survey of Imitation Learning Methods, Environments and Metricscited by 16
  27. 2026Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modelingcited by 15
  28. 2023Learning from Visual Observation via Offline Pretrained State-to-Go Transformercited by 14
  29. 2025PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planningcited by 14
  30. 2021Imitation by Predicting Observationscited by 13
  31. 2021Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Taskscited by 13
  32. 2022Imitation Learning from Observations under Transition Model Disparitycited by 11
  33. 2023Domain Adaptive Imitation Learning with Visual Observationcited by 11
  34. 2025Closing the Train-Test Gap in World Models for Gradient-Based Planningcited by 11
  35. 2022Adversarial Imitation Learning from Video using a State Observercited by 10
  36. 2023Imitation Learning from Observation with Automatic Discount Schedulingcited by 10
  37. 2024AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual Distractorscited by 10
  38. 2024A Dual Approach to Imitation Learning from Observations with Offline Datasetscited by 10

50 most cited of 101 All 101 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2020Imitating Unknown Policies via Exploration
  2. 2026When Does On-Policy Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning
  3. 2022Causal Imitation Learning under Temporally Correlated Noise
  4. 2022Information-Theoretic Policy Learning from Partial Observations with Fully Informed Decision Makers
  5. 2023Invariant Causal Imitation Learning for Generalizable Policies
  6. 2018Fast Policy Learning through Imitation and Reinforcement
  7. 2022Deconfounding Imitation Learning with Variational Inference
  8. 2019Causal Confusion in Imitation Learning