# DeepLine: AutoML Tool for Pipelines Generation using Deep Reinforcement Learning and Hierarchical Actions Filtering

arXiv: https://arxiv.org/abs/1911.00061 · HTML: https://mlsanity.com/paper/1911.00061/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2019.

## Built on by (most cited first, 21 of 21)

- [Data-centric Artificial Intelligence: A Survey](https://mlsanity.com/paper/2303.10158/) (2023)
- [Data-centric AI: Perspectives and Challenges](https://mlsanity.com/paper/2301.04819/) (2023)
- [Automated Evolutionary Approach for the Design of Composite Machine Learning Pipelines](https://mlsanity.com/paper/2106.15397/) (2021)
- [AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework](https://mlsanity.com/paper/2412.10422/) (2024)
- [A Survey on Deep Reinforcement Learning for Data Processing and Analytics](https://mlsanity.com/paper/2108.04526/) (2021)
- [Towards Automated Imbalanced Learning with Deep Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2208.12433/) (2022)
- [SubStrat: A Subset-Based Strategy for Faster AutoML](https://mlsanity.com/paper/2206.03070/) (2022)
- [ChainBuddy: An AI Agent System for Generating LLM Pipelines](https://mlsanity.com/paper/2409.13588/) (2024)
- [Multi-Objective Evolutionary Design of Composite Data-Driven Models](https://mlsanity.com/paper/2103.01301/) (2021)
- [HyperSHAP: Shapley Values and Interactions for Explaining Hyperparameter Optimization](https://mlsanity.com/paper/2502.01276/) (2025)
- [CleanSurvival: Automated data preprocessing for time-to-event models using reinforcement learning](https://mlsanity.com/paper/2502.03946/) (2025)
- [Towards Personalized Preprocessing Pipeline Search](https://mlsanity.com/paper/2302.14329/) (2023)
- [EDCA - An Evolutionary Data-Centric AutoML Framework for Efficient Pipelines](https://mlsanity.com/paper/2503.04350/) (2025)
- [LLaPipe: LLM-Guided Reinforcement Learning for Automated Data Preparation Pipeline Construction](https://mlsanity.com/paper/2507.13712/) (2025)
- [Aixel: A Unified, Adaptive and Extensible System for AI-powered Data Analysis](https://mlsanity.com/paper/2510.12642/) (2025)
- [AutoMC: Automated Model Compression based on Domain Knowledge and Progressive search strategy](https://mlsanity.com/paper/2201.09884/) (2022)
- [Grammar-based evolutionary approach for automated workflow composition with domain-specific operators and ensemble diversity](https://mlsanity.com/paper/2402.02124/) (2024)
- [Data Acquisition for Improving Model Fairness using Reinforcement Learning](https://mlsanity.com/paper/2412.03009/) (2024)
- [SoftPipe: A Soft-Guided Reinforcement Learning Framework for Automated Data Preparation](https://mlsanity.com/paper/2507.13710/) (2025)
- [From Intent to AI Pipelines: A Controlled Agentic Framework for Non-AI Expert Scientists](https://mlsanity.com/paper/2605.18764/) (2026)
- [FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction](https://mlsanity.com/paper/2606.24679/) (2026)

## Abstract (arXiv)

Automatic machine learning (AutoML) is an area of research aimed at automating machine learning (ML) activities that currently require human experts. One of the most challenging tasks in this field is the automatic generation of end-to-end ML pipelines: combining multiple types of ML algorithms into a single architecture used for end-to-end analysis of previously-unseen data. This task has two challenging aspects: the first is the need to explore a large search space of algorithms and pipeline architectures. The second challenge is the computational cost of training and evaluating multiple pipelines. In this study we present DeepLine, a reinforcement learning based approach for automatic pipeline generation. Our proposed approach utilizes an efficient representation of the search space and leverages past knowledge gained from previously-analyzed datasets to make the problem more tractable. Additionally, we propose a novel hierarchical-actions algorithm that serves as a plugin, mediating the environment-agent interaction in deep reinforcement learning problems. The plugin significantly speeds up the training process of our model. Evaluation on 56 datasets shows that DeepLine outperforms state-of-the-art approaches both in accuracy and in computational cost.