mlsanityData to 14 Oct 2026

One-Shot Imitation Learning

arXiv 1703.07326 ↗First posted 21 Mar 2017cs.AI cs.LG cs.NEcited by 233

Not on the map. Why?

Cited by 113 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Imitation learning has been commonly applied to solve different tasks in isolation. This usually requires either careful feature engineering, or a significant number of samples. This is far from what we desire: ideally, robots should be able to learn from very few demonstrations of any given task, and instantly generalize to new situations of the same task, without requiring task-specific engineering. In this paper, we propose a meta-learning framework for achieving such capability, which we call one-shot imitation learning. Specifically, we consider the setting where there is a very large set of tasks, and each task has many instantiations. For example, a task could be to stack all blocks on a table into a single tower, another task could be to place all blocks on a table into two-block towers, etc. In each case, different instances of the task would consist of different sets of blocks with different initial states. At training time, our algorithm is presented with pairs of demonstrations for a subset of all tasks. A neural net is trained that takes as input one demonstration and the current state (which initially is the initial state of the other demonstration of the pair), and outputs an action with the goal that the resulting sequence of states and actions matches as closely as possible with the second demonstration. At test time, a demonstration of a single instance of a new task is presented, and the neural net is expected to perform well on new instances of this new task. The use of soft attention allows the model to generalize to conditions and tasks unseen in the training data. We anticipate that by training this model on a much greater variety of tasks and settings, we will obtain a general system that can turn any demonstrations into robust policies that can accomplish an overwhelming variety of tasks. Videos available at https://bit.ly/nips2017-oneshot .

Key facts. Cited by 233 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 11; 2019: 11; 2020: 6; 2021: 35; 2022: 40; 2023: 40; 2024: 44; 2025: 27; 2026: 19.

233 papers.

Sort:

By area:

  1. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  2. 2021How Attentive are Graph Attention Networks?cited by 835
  3. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 523
  4. 2018An Algorithmic Perspective on Imitation Learningcited by 459
  5. 2022VIMA: General Robot Manipulation with Multimodal Promptscited by 407
  6. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 391
  7. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 250
  8. 2021MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scalecited by 229
  9. 2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 213
  10. 2023RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shotcited by 183
  11. 2022Human-to-Robot Imitation in the Wildcited by 161
  12. 2021The Surprising Effectiveness of Representation Learning for Visual Imitationcited by 154
38 more
  1. 2022Prompting Decision Transformer for Few-Shot Policy Generalizationcited by 146
  2. 2023FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulationcited by 133
  3. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 126
  4. 2024HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulationcited by 112
  5. 2021Generalized Decision Transformer for Offline Hindsight Information Matchingcited by 106
  6. 2022From Play to Policy: Conditional Behavior Generation from Uncurated Robot Datacited by 103
  7. 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 103
  8. 2021Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstrationcited by 93
  9. 2024Vision Language Models are In-Context Value Learnerscited by 90
  10. 2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
  11. 2021Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulationcited by 83
  12. 2022You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstrationcited by 81
  13. 2023Preference Transformer: Modeling Human Preferences using Transformers for RLcited by 79
  14. 2023XSkill: Cross Embodiment Skill Discoverycited by 75
  15. 2024EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learningcited by 75
  16. 2024Keypoint Action Tokens Enable In-Context Imitation Learning in Roboticscited by 74
  17. 2021Asymmetric self-play for automatic goal discovery in robotic manipulationcited by 72
  18. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  19. 2021Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapescited by 71
  20. 2023SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Executioncited by 70
  21. 2024In-Context Imitation Learning via Next-Token Predictioncited by 70
  22. 2022MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrationscited by 62
  23. 2023Learning Generalizable Manipulation Policies with Object-Centric 3D Representationscited by 61
  24. 2025Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learningcited by 59
  25. 2021Imitation Learning: Progress, Taxonomies and Challengescited by 58
  26. 2023Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasetscited by 58
  27. 2024Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstructioncited by 54
  28. 2024Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformerscited by 52
  29. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 51
  30. 2019Meta-Inverse Reinforcement Learning with Probabilistic Context Variablescited by 50
  31. 2022Imitation Learning by Estimating Expertise of Demonstratorscited by 50
  32. 2024Vision-based Manipulation from Single Human Video with Open-World Object Graphscited by 50
  33. 2021Towards More Generalizable One-shot Visual Imitation Learningcited by 49
  34. 2021SORNet: Spatial Object-Centric Representations for Sequential Manipulationcited by 48
  35. 2019Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreementcited by 46
  36. 2019Task-Relevant Adversarial Imitation Learningcited by 45
  37. 2021AGENT: A Benchmark for Core Psychological Reasoningcited by 42
  38. 2024PoCo: Policy Composition from and for Heterogeneous Robot Learningcited by 42

50 most cited of 233 All 233 (JSON)