mlsanityData to 14 Oct 2026

One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks

arXiv 1810.11043 ↗First posted 25 Oct 2018cs.LG cs.AI cs.CVcited by 33

On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning

Abstract (arXiv)

We consider the problem of learning multi-stage vision-based tasks on a real robot from a single video of a human performing the task, while leveraging demonstration data of subtasks with other objects. This problem presents a number of major challenges. Video demonstrations without teleoperation are easy for humans to provide, but do not provide any direct supervision. Learning policies from raw pixels enables full generality but calls for large function approximators with many parameters to be learned. Finally, compound tasks can require impractical amounts of demonstration data, when treated as a monolithic skill. To address these challenges, we propose a method that learns both how to learn primitive behaviors from video demonstrations and how to dynamically compose these behaviors to perform multi-stage tasks by "watching" a human demonstrator. Our results on a simulated Sawyer robot and real PR2 robot illustrate our method for learning a variety of order fulfillment and kitchen serving tasks with novel objects and raw pixel inputs.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 17 of its 38 references that are in the map. First posted on arXiv 25 Oct 2018.

Builds on

17 of 38 references.

References · 17

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2016Layer Normalizationcited by 5,669
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  5. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 459
  6. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 289
  7. 2017One-Shot Imitation Learningcited by 233
  8. 2017Searching for Activation Functionscited by 169
  9. 2017Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translationcited by 167
  10. 2018One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learningcited by 148
  11. 2017Third-Person Imitation Learningcited by 103
  12. 2017Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstrationcited by 100
5 more
  1. 2017Neural Task Programming: Learning to Generalize Across Hierarchical Taskscited by 76
  2. 2017Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Netscited by 64
  3. 2018TACO: Learning Task Decomposition via Temporal Alignment for Controlcited by 62
  4. 2018Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstrationcited by 61
  5. 2017Translating Videos to Commands for Robotic Manipulation with Deep Recurrent Neural Networkscited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 3; 2020: 3; 2021: 12; 2022: 4; 2023: 4; 2024: 4; 2025: 2; 2026: 1.

33 papers.

Sort:

By area:

  1. 2021MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scalecited by 229
  2. 2021Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulationcited by 83
  3. 2023XSkill: Cross Embodiment Skill Discoverycited by 75
  4. 2023LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discoverycited by 67
  5. 2023Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasetscited by 58
  6. 2019Meta-Inverse Reinforcement Learning with Probabilistic Context Variablescited by 50
  7. 2020Deep Imitation Learning for Bimanual Robotic Manipulationcited by 50
  8. 2021SORNet: Spatial Object-Centric Representations for Sequential Manipulationcited by 48
  9. 2019Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems with Heterogeneous Sensor Datacited by 24
  10. 2021CRIL: Continual Robot Imitation Learning via Generative and Prediction Modelcited by 24
  11. 2021Causal Navigation by Continuous-time Neural Networkscited by 23
  12. 2021Learning Multi-Stage Tasks with One Demonstration via Self-Replaycited by 21
21 more
  1. 2021Adversarial Option-Aware Hierarchical Imitation Learningcited by 19
  2. 2021Guided Imitation of Task and Motion Planningcited by 18
  3. 2022Cross-Domain Transfer via Semantic Skill Imitationcited by 18
  4. 2023Multi-task Hierarchical Adversarial Inverse Reinforcement Learningcited by 15
  5. 2022An Independently Learnable Hierarchical Model for Bilateral Control-Based Imitation Learning Applicationscited by 14
  6. 2025Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulationcited by 14
  7. 2021Example-Driven Model-Based Reinforcement Learning for Solving Long-Horizon Visuomotor Taskscited by 13
  8. 2019To Follow or not to Follow: Selective Imitation Learning from Observationscited by 10
  9. 2021Towards Robust One-shot Task Execution using Knowledge Graph Embeddingscited by 8
  10. 2022Transfering Hierarchical Structure with Dual Meta Imitation Learningcited by 7
  11. 2024One-shot Imitation in a Non-Stationary Environment via Multi-Modal Skillcited by 7
  12. 2022Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gapcited by 5
  13. 2026Robot Learning from Human Videos: A Surveycited by 5
  14. 2020Imitation Learning for High Precision Peg-in-Hole Taskscited by 3
  15. 2021Online Baum-Welch algorithm for Hierarchical Imitation Learningcited by 3
  16. 2025Trajectory Conditioned Cross-embodiment Skill Transfercited by 3
  17. 2021Off-policy Imitation Learning from Visual Inputscited by 2
  18. 2024Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learningcited by 2
  19. 2020Multi-Instance Aware Localization for End-to-End Imitation Learningcited by 0
  20. 2024On the benefits of pixel-based hierarchical policies for task generalizationcited by 0
  21. 2024One-Shot Robust Imitation Learning for Long-Horizon Visuomotor Tasks from Unsegmented Demonstrationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration
  2. 2026Human-to-Robot Interaction: Learning from Video Demonstration for Robot Imitation
  3. 2019Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller
  4. 2021Towards More Generalizable One-shot Visual Imitation Learning
  5. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skills
  6. 2022Learning Sensorimotor Primitives of Sequential Manipulation Tasks from Visual Demonstrations
  7. 2020Goal-Conditioned End-to-End Visuomotor Control for Versatile Skill Primitives
  8. 2021Seeing All the Angles: Learning Multiview Manipulation Policies for Contact-Rich Tasks from Demonstrations