# Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning

arXiv: https://arxiv.org/abs/1908.06769 · HTML: https://mlsanity.com/paper/1908.06769/

## Key facts

- Cited by 8 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 14 of its 33 references that are in the map.
- First posted on arXiv 16 Aug 2019.

## 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, 14 of 14)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Neural Module Networks](https://mlsanity.com/paper/1511.02799/) (2015)
- [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)
- [Zero-Shot Visual Imitation](https://mlsanity.com/paper/1804.08606/) (2018)
- [Neural Task Programming: Learning to Generalize Across Hierarchical Tasks](https://mlsanity.com/paper/1710.01813/) (2017)
- [TACO: Learning Task Decomposition via Temporal Alignment for Control](https://mlsanity.com/paper/1803.01840/) (2018)
- [Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration](https://mlsanity.com/paper/1807.03480/) (2018)
- [Online Planning Algorithms for POMDPs](https://mlsanity.com/paper/1401.3436/) (2014)
- [Learning Heuristic Search via Imitation](https://mlsanity.com/paper/1707.03034/) (2017)
- [One-Shot Learning of Multi-Step Tasks from Observation via Activity Localization in Auxiliary Video](https://mlsanity.com/paper/1806.11244/) (2018)
- [Learning Quickly to Plan Quickly Using Modular Meta-Learning](https://mlsanity.com/paper/1809.07878/) (2018)

## Built on by (most cited first, 8 of 8)

- [Towards More Generalizable One-shot Visual Imitation Learning](https://mlsanity.com/paper/2110.13423/) (2021)
- [Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution](https://mlsanity.com/paper/2103.14230/) (2021)
- [Predicting Stable Configurations for Semantic Placement of Novel Objects](https://mlsanity.com/paper/2108.12062/) (2021)
- [Learning Multi-Stage Tasks with One Demonstration via Self-Replay](https://mlsanity.com/paper/2111.07447/) (2021)
- [Motion Reasoning for Goal-Based Imitation Learning](https://mlsanity.com/paper/1911.05864/) (2019)
- [One-shot Visual Imitation via Attributed Waypoints and Demonstration Augmentation](https://mlsanity.com/paper/2302.04856/) (2023)
- [6-DoF Stability Field via Diffusion Models](https://mlsanity.com/paper/2310.17649/) (2023)
- [Learning Symbolic Operators: A Neurosymbolic Solution for Autonomous Disassembly of Electric Vehicle Battery](https://mlsanity.com/paper/2206.03027/) (2022)

## Abstract (arXiv)

We address one-shot imitation learning, where the goal is to execute a previously unseen task based on a single demonstration. While there has been exciting progress in this direction, most of the approaches still require a few hundred tasks for meta-training, which limits the scalability of the approaches. Our main contribution is to formulate one-shot imitation learning as a symbolic planning problem along with the symbol grounding problem. This formulation disentangles the policy execution from the inter-task generalization and leads to better data efficiency. The key technical challenge is that the symbol grounding is prone to error with limited training data and leads to subsequent symbolic planning failures. We address this challenge by proposing a continuous relaxation of the discrete symbolic planner that directly plans on the probabilistic outputs of the symbol grounding model. Our continuous relaxation of the planner can still leverage the information contained in the probabilistic symbol grounding and significantly improve over the baseline planner for the one-shot imitation learning tasks without using large training data.