The efficient exploration of chemical space remains a central challenge, as many generative models still produce unstable or non-synthesizable compounds. To address these limitations, we present EvoMol-RL, a significant extension of the EvoMol evolutionary algorithm that integrates reinforcement learning to guide molecular mutations based on local structural context. By leveraging Extended Connectivity Fingerprints (ECFPs), EvoMol-RL learns context-aware mutation policies that prioritize chemically plausible transformations. This approach significantly improves the generation of valid and realistic molecules, reducing the frequency of structural artifacts and enhancing optimization performance. The results demonstrate that EvoMol-RL consistently outperforms its baseline in molecular pre-filtering realism. These results emphasize the effectiveness of combining reinforcement learning with molecular fingerprints to generate chemically relevant molecular structures.
@article{arxiv.2510.00802,
title = {Guiding Evolutionary Molecular Design: Adding Reinforcement Learning for Mutation Selection},
author = {Gaelle Milon-Harnois and Chaimaa Touhami and Nicolas Gutowski and Benoit Da Mota and Thomas Cauchy},
journal= {arXiv preprint arXiv:2510.00802},
year = {2025}
}
Comments
8 pages, 3 figures, Accepted for publication in the proceedings of ICTAI 2025