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

arXiv: https://arxiv.org/abs/2112.02278 · HTML: https://mlsanity.com/paper/2112.02278/

## Key facts

- Cited by 2 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 31 references that are in the map.
- First posted on arXiv 4 Dec 2021.

## Placed in

- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 17 of 17)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [One-Shot Imitation Learning](https://mlsanity.com/paper/1703.07326/) (2017)
- [One-Shot Visual Imitation Learning via Meta-Learning](https://mlsanity.com/paper/1709.04905/) (2017)
- [One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning](https://mlsanity.com/paper/1802.01557/) (2018)
- [Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning](https://mlsanity.com/paper/1803.09956/) (2018)
- [Task-Embedded Control Networks for Few-Shot Imitation Learning](https://mlsanity.com/paper/1810.03237/) (2018)
- [PyRep: Bringing V-REP to Deep Robot Learning](https://mlsanity.com/paper/1906.11176/) (2019)
- [Learning One-Shot Imitation from Humans without Humans](https://mlsanity.com/paper/1911.01103/) (2019)
- [Differentiable Meta-learning Model for Few-shot Semantic Segmentation](https://mlsanity.com/paper/1911.10371/) (2019)
- [Few-Shot Bayesian Imitation Learning with Logical Program Policies](https://mlsanity.com/paper/1904.06317/) (2019)
- [Towards Hierarchical Task Decomposition using Deep Reinforcement Learning for Pick and Place Subtasks](https://mlsanity.com/paper/2102.04022/) (2021)

## Built on by (most cited first, 2 of 2)

- [DITTO: Demonstration Imitation by Trajectory Transformation](https://mlsanity.com/paper/2403.15203/) (2024)
- [Imitator Learning: Achieve Out-of-the-Box Imitation Ability in Variable Environments](https://mlsanity.com/paper/2310.05712/) (2023)

## 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.