# Dual-Agent Reinforcement Learning for Automated Feature Generation

arXiv: https://arxiv.org/abs/2505.12628 · HTML: https://mlsanity.com/paper/2505.12628/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL with diffusion and flow models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 14 of its 32 references that are in the map.
- First posted on arXiv 19 May 2025.

## Placed in

- Deep reinforcement learning methods / [RL with diffusion and flow models](https://mlsanity.com/deeprl/rl-with-diffusion-and-flow-models/)

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [TabTransformer: Tabular Data Modeling Using Contextual Embeddings](https://mlsanity.com/paper/2012.06678/) (2020)
- [Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation](https://mlsanity.com/paper/1604.06057/) (2016)
- [A Critical Review of Recurrent Neural Networks for Sequence Learning](https://mlsanity.com/paper/1506.00019/) (2015)
- [Feature Engineering for Predictive Modeling using Reinforcement Learning](https://mlsanity.com/paper/1709.07150/) (2017)
- [The autofeat Python Library for Automated Feature Engineering and Selection](https://mlsanity.com/paper/1901.07329/) (2019)
- [AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications](https://mlsanity.com/paper/1904.12857/) (2019)
- [Group-wise Reinforcement Feature Generation for Optimal and Explainable Representation Space Reconstruction](https://mlsanity.com/paper/2205.14526/) (2022)
- [Self-optimizing Feature Generation via Categorical Hashing Representation and Hierarchical Reinforcement Crossing](https://mlsanity.com/paper/2309.04612/) (2023)
- [Techniques for Automated Machine Learning](https://mlsanity.com/paper/1907.08908/) (2019)
- [TFWT: Tabular Feature Weighting with Transformer](https://mlsanity.com/paper/2405.08403/) (2024)
- [Self-Optimizing Feature Transformation](https://mlsanity.com/paper/2209.08044/) (2022)
- [Efficient Hierarchical Storage Management Framework Empowered by Reinforcement Learning](https://mlsanity.com/paper/2201.11668/) (2022)

## Built on by (most cited first, 1 of 1)

- [Flat-Consensus Diffusion for Robust Data Reshaping under Noisy Evaluator](https://mlsanity.com/paper/2609.32696/) (2026)

## Abstract (arXiv)

Feature generation involves creating new features from raw data to capture complex relationships among the original features, improving model robustness and machine learning performance. Current methods using reinforcement learning for feature generation have made feature exploration more flexible and efficient. However, several challenges remain: first, during feature expansion, a large number of redundant features are generated. When removing them, current methods only retain the best features each round, neglecting those that perform poorly initially but could improve later. Second, the state representation used by current methods fails to fully capture complex feature relationships. Third, there are significant differences between discrete and continuous features in tabular data, requiring different operations for each type. To address these challenges, we propose a novel dual-agent reinforcement learning method for feature generation. Two agents are designed: the first generates new features, and the second determines whether they should be preserved. A self-attention mechanism enhances state representation, and diverse operations distinguish interactions between discrete and continuous features. The experimental results on multiple datasets demonstrate that the proposed method is effective. The code is available at https://github.com/extess0/DARL.