Inverse chemical design using generative deep learning (DL) models is an emerging tool, which has early success in generating molecular structures with desired properties. We enhance this tool by developing heuristics for curriculum-learning based multiple-objective (20+ objectives) reinforcement learning, and apply it to the context of chemical identi?cation. We develop a generative DL framework that utilizes constraints pertaining to the unknown molecule’s mass and functional group composition, and show that multiple-objective RL-based generative DL models can correctly identify unknown molecules with a 80% success rate, compared to the baseline approach of 0%. Lastly, the heuristics developed are not limited to just chemistry research challenges; we anticipate any problem that utilizes reinforcement learning with multiple-objectives will bene?t from it.
Revised: December 22, 2020 |
Published: December 28, 2018
Citation
Wei H., M.V. Olarte, and G.B. Goh. 2018.Multiple-objective Reinforcement Learning for Inverse Design and Identification. In Proceedings of the 32nd Conference on Neural Information Processing Systems (NeurlPS 2018), December 3-8, 2018, Montreal, Canada, edited by S. Bengio, et al. Red Hook, New York:Curran Associates, Inc.PNNL-SA-139575.