Guiding Evolutionary Molecular Design: Adding Reinforcement Learning for Mutation Selection
This addresses the problem of inefficient chemical space exploration for drug discovery or materials science, but it is incremental as it builds on an existing evolutionary method.
The paper tackled the challenge of generating stable and synthesizable molecules by extending the EvoMol evolutionary algorithm with reinforcement learning to guide mutations based on structural context, resulting in improved generation of valid molecules and reduced artifacts.
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.