# A Reinforcement Learning Approach to Synthetic Data Generation

arXiv: https://arxiv.org/abs/2512.21395 · HTML: https://mlsanity.com/paper/2512.21395/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Membership inference attacks, one of 12 directions in LLM safety and security.
- Builds on 21 of its 54 references that are in the map.
- First posted on arXiv 24 Dec 2025.

## Placed in

- LLM safety and security / [Membership inference attacks](https://mlsanity.com/safety/membership-inference-attacks/)
- 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, 21 of 21)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient](https://mlsanity.com/paper/1609.05473/) (2016)
- [GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification](https://mlsanity.com/paper/1803.01229/) (2018)
- [A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models](https://mlsanity.com/paper/1611.03852/) (2016)
- [Generative models improve fairness of medical classifiers under distribution shifts](https://mlsanity.com/paper/2304.09218/) (2023)
- [CTAB-GAN+: Enhancing Tabular Data Synthesis](https://mlsanity.com/paper/2204.00401/) (2022)
- [Membership Inference Attacks against Synthetic Data through Overfitting Detection](https://mlsanity.com/paper/2302.12580/) (2023)
- [A Multifaceted Benchmarking of Synthetic Electronic Health Record Generation Models](https://mlsanity.com/paper/2208.01230/) (2022)
- [Why Spectral Normalization Stabilizes GANs: Analysis and Improvements](https://mlsanity.com/paper/2009.02773/) (2020)
- [EHRDiff: Exploring Realistic EHR Synthesis with Diffusion Models](https://mlsanity.com/paper/2303.05656/) (2023)
- [Synthetically Enhanced: Unveiling Synthetic Data's Potential in Medical Imaging Research](https://mlsanity.com/paper/2311.09402/) (2023)
- [Synthesize High-dimensional Longitudinal Electronic Health Records via Hierarchical Autoregressive Language Model](https://mlsanity.com/paper/2304.02169/) (2023)
- [Controllable Synthetic Clinical Note Generation with Privacy Guarantees](https://mlsanity.com/paper/2409.07809/) (2024)

## Abstract (arXiv)

Synthetic data generation (SDG) is a promising approach for enabling data sharing in biomedical studies while preserving patient privacy. Yet, state-of-the-art generative models often require large datasets and complex training procedures, limiting their applicability in small-sample settings common in biomedical research. This study aims to develop a more principled and efficient approach to SDG and evaluate its efficacy for biomedical applications. In this work, we reframe SDG as a reinforcement learning (RL) problem and introduce RLSyn, a novel framework that models the data generator as a stochastic policy over patient records and optimizes it using Proximal Policy Optimization with discriminator-derived rewards. We evaluate RLSyn on two biomedical datasets--AI-READI and MIMIC-IV--and benchmark it against state-of-the-art generative adversarial networks (GANs) and diffusion-based methods across extensive privacy, utility, and fidelity evaluations. On MIMIC-IV, RLSyn achieves predictive utility comparable to diffusion models (S2R AUC 0.902 vs 0.906 respectively) while slightly outperforming them in fidelity (NMI 0.001 vs. 0.003; DWD 2.073 vs. 2.797) and achieving comparable, low privacy risk (~0.50 membership inference risk AUC). On the smaller AI-READI dataset, RLSyn again matches diffusion-based utility (S2R AUC 0.873 vs. 0.871), while achieving higher fidelity (NMI 0.001 vs. 0.002; DWD 13.352 vs. 16.441) and significantly lower vulnerability to membership inference attacks (AUC 0.544 vs. 0.601). Both RLSyn and diffusion-based models substantially outperform GANs across utility and fidelity on both datasets. Our results suggest that reinforcement learning provides a principled and effective approach for synthetic biomedical data generation, particularly in data-scarce regimes.