# Augmenting Policy Learning with Routines Discovered from a Single Demonstration

arXiv: https://arxiv.org/abs/2012.12469 · HTML: https://mlsanity.com/paper/2012.12469/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- First posted on arXiv 23 Dec 2020.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Built on by (most cited first, 6 of 6)

- [RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning](https://mlsanity.com/paper/2212.01737/) (2022)
- [Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation](https://mlsanity.com/paper/2602.03045/) (2026)
- [Boosting Reinforcement Learning and Planning with Demonstrations: A Survey](https://mlsanity.com/paper/2303.13489/) (2023)
- [WorldBagel: Uncovering the Power of Unified Multimodal Models for Vision-Language-Action-World Modeling](https://mlsanity.com/paper/2607.03461/) (2026)
- [Harnessing LLMs as Agents: What Does It Cost?](https://mlsanity.com/paper/2610.02488/) (2026)
- [Can Language Models Learn to Reject Their Own Bad Reasoning Steps?](https://mlsanity.com/paper/2610.05976/) (2026)

## Abstract (arXiv)

Humans can abstract prior knowledge from very little data and use it to boost skill learning. In this paper, we propose routine-augmented policy learning (RAPL), which discovers routines composed of primitive actions from a single demonstration and uses discovered routines to augment policy learning. To discover routines from the demonstration, we first abstract routine candidates by identifying grammar over the demonstrated action trajectory. Then, the best routines measured by length and frequency are selected to form a routine library. We propose to learn policy simultaneously at primitive-level and routine-level with discovered routines, leveraging the temporal structure of routines. Our approach enables imitating expert behavior at multiple temporal scales for imitation learning and promotes reinforcement learning exploration. Extensive experiments on Atari games demonstrate that RAPL improves the state-of-the-art imitation learning method SQIL and reinforcement learning method A2C. Further, we show that discovered routines can generalize to unseen levels and difficulties on the CoinRun benchmark.