mlsanityData to 13 Oct 2026

Stage Conscious Attention Network (SCAN) : A Demonstration-Conditioned Policy for Few-Shot Imitation

arXiv 2112.02278 ↗First posted 4 Dec 2021cs.RO cs.AIcited by 2

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

Abstract (arXiv)

In few-shot imitation learning (FSIL), using behavioral cloning (BC) to solve unseen tasks with few expert demonstrations becomes a popular research direction. The following capabilities are essential in robotics applications: (1) Behaving in compound tasks that contain multiple stages. (2) Retrieving knowledge from few length-variant and misalignment demonstrations. (3) Learning from a different expert. No previous work can achieve these abilities at the same time. In this work, we conduct FSIL problem under the union of above settings and introduce a novel stage conscious attention network (SCAN) to retrieve knowledge from few demonstrations simultaneously. SCAN uses an attention module to identify each stage in length-variant demonstrations. Moreover, it is designed under demonstration-conditioned policy that learns the relationship between experts and agents. Experiment results show that SCAN can learn from different experts without fine-tuning and outperform baselines in complicated compound tasks with explainable visualization.

Key facts. Cited by 2 papers in the map (data through 13 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 31 references that are in the map. First posted on arXiv 4 Dec 2021.

Builds on

17 of 31 references.

Closest ancestors · 2

Same direction, newest first

  1. 2019Learning One-Shot Imitation from Humans without Humans4 Nov
  2. 2018Task-Embedded Control Networks for Few-Shot Imitation Learning8 Oct

Other references · 15

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,870
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,011
  3. 2016Matching Networks for One Shot Learningcited by 2,251
  4. 2016Generative Adversarial Imitation Learningcited by 1,577
  5. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,141
  6. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,025
  7. 2018Self-Attention Generative Adversarial Networkscited by 809
  8. 2017One-Shot Imitation Learningcited by 232
  9. 2017One-Shot Visual Imitation Learning via Meta-Learningcited by 225
  10. 2018One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learningcited by 146
  11. 2018Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learningcited by 121
  12. 2019PyRep: Bringing V-REP to Deep Robot Learningcited by 43
3 more
  1. 2019Differentiable Meta-learning Model for Few-shot Semantic Segmentationcited by 31
  2. 2019Few-Shot Bayesian Imitation Learning with Logical Program Policiescited by 30
  3. 2021Towards Hierarchical Task Decomposition using Deep Reinforcement Learning for Pick and Place Subtaskscited by 13

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2024DITTO: Demonstration Imitation by Trajectory Transformationcited by 29
  2. 2023Imitator Learning: Achieve Out-of-the-Box Imitation Ability in Variable Environmentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Rational Inverse Reasoning: Few-Shot Imitation by Inferring Intent through Planning
  2. 2021Towards More Generalizable One-shot Visual Imitation Learning
  3. 2023Memory-Consistent Neural Networks for Imitation Learning
  4. 2024Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control
  5. 2026Difference-Aware Retrieval Policies for Imitation Learning
  6. 2024Imitation Learning from Suboptimal Demonstrations via Meta-Learning An Action Ranker
  7. 2020Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations
  8. 2024Robotic Imitation of Human Actions