# Automatic Machine Learning by Pipeline Synthesis using Model-Based Reinforcement Learning and a Grammar

arXiv: https://arxiv.org/abs/1905.10345 · HTML: https://mlsanity.com/paper/1905.10345/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2019.

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

- [Incremental Search Space Construction for Machine Learning Pipeline Synthesis](https://mlsanity.com/paper/2101.10951/) (2021)
- [DISeR: Designing Imaging Systems with Reinforcement Learning](https://mlsanity.com/paper/2309.13851/) (2023)
- [Privileged Zero-Shot AutoML](https://mlsanity.com/paper/2106.13743/) (2021)
- [CleanSurvival: Automated data preprocessing for time-to-event models using reinforcement learning](https://mlsanity.com/paper/2502.03946/) (2025)
- [Generating Skyline Datasets for Data Science Models](https://mlsanity.com/paper/2502.11262/) (2025)
- [A Survey of Open Source Automation Tools for Data Science Predictions](https://mlsanity.com/paper/2208.11792/) (2022)
- [Clustering Indices based Automatic Classification Model Selection](https://mlsanity.com/paper/2305.13926/) (2023)
- [Integrating Hyperparameter Search into Model-Free AutoML with Context-Free Grammars](https://mlsanity.com/paper/2404.03419/) (2024)

## Abstract (arXiv)

Automatic machine learning is an important problem in the forefront of machine learning. The strongest AutoML systems are based on neural networks, evolutionary algorithms, and Bayesian optimization. Recently AlphaD3M reached state-of-the-art results with an order of magnitude speedup using reinforcement learning with self-play. In this work we extend AlphaD3M by using a pipeline grammar and a pre-trained model which generalizes from many different datasets and similar tasks. Our results demonstrate improved performance compared with our earlier work and existing methods on AutoML benchmark datasets for classification and regression tasks. In the spirit of reproducible research we make our data, models, and code publicly available.