# Distributed Reinforcement Learning for Molecular Design: Antioxidant case

arXiv: https://arxiv.org/abs/2312.01267 · HTML: https://mlsanity.com/paper/2312.01267/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 36 references that are in the map.
- First posted on arXiv 3 Dec 2023.

## Builds on (most cited first, 8 of 8)

- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation](https://mlsanity.com/paper/1806.02473/) (2018)
- [GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation](https://mlsanity.com/paper/2001.09382/) (2020)
- [Optimization of Molecules via Deep Reinforcement Learning](https://mlsanity.com/paper/1810.08678/) (2018)
- [Deep Reinforcement Learning for De-Novo Drug Design](https://mlsanity.com/paper/1711.10907/) (2017)
- [Scalable Online Planning via Reinforcement Learning Fine-Tuning](https://mlsanity.com/paper/2109.15316/) (2021)
- [Generating stable molecules using imitation and reinforcement learning](https://mlsanity.com/paper/2107.05007/) (2021)
- [Application of quantum-inspired generative models to small molecular datasets](https://mlsanity.com/paper/2304.10867/) (2023)

## Abstract (arXiv)

Deep reinforcement learning has successfully been applied for molecular discovery as shown by the Molecule Deep Q-network (MolDQN) algorithm. This algorithm has challenges when applied to optimizing new molecules: training such a model is limited in terms of scalability to larger datasets and the trained model cannot be generalized to different molecules in the same dataset. In this paper, a distributed reinforcement learning algorithm for antioxidants, called DA-MolDQN is proposed to address these problems. State-of-the-art bond dissociation energy (BDE) and ionization potential (IP) predictors are integrated into DA-MolDQN, which are critical chemical properties while optimizing antioxidants. Training time is reduced by algorithmic improvements for molecular modifications. The algorithm is distributed, scalable for up to 512 molecules, and generalizes the model to a diverse set of molecules. The proposed models are trained with a proprietary antioxidant dataset. The results have been reproduced with both proprietary and public datasets. The proposed molecules have been validated with DFT simulations and a subset of them confirmed in public "unseen" datasets. In summary, DA-MolDQN is up to 100x faster than previous algorithms and can discover new optimized molecules from proprietary and public antioxidants.