Exploring Potential Energy Surfaces Using Reinforcement Machine Learning

Reinforcement machine learning is implemented to survey a series of model potential energy surfaces and ultimately identify the global minima point. Through sophisticated reward function design, the introduction of an optimizing target, and incorporating physically motivated actions, the reinforceme...

Full description

Saved in:
Bibliographic Details
Published in:Journal of chemical information and modeling 2022-07, Vol.62 (13), p.3169-3179
Main Authors: Mills, Alexis W., Goings, Joshua J., Beck, David, Yang, Chao, Li, Xiaosong
Format: Article
Language:English
Subjects:
Decision making
Design optimization
Feasibility studies
Machine learning
Machine Learning and Deep Learning
Minima
Potential energy
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Reinforcement machine learning is implemented to survey a series of model potential energy surfaces and ultimately identify the global minima point. Through sophisticated reward function design, the introduction of an optimizing target, and incorporating physically motivated actions, the reinforcement learning agent is capable of demonstrating advanced decision making. These improved actions allow the agent to successfully converge to an optimal solution more rapidly when compared to an agent trained without the aforementioned modifications. This study showcases the conceptual feasibility of using reinforcement machine learning to solve difficult environments, namely, potential energy surfaces, with multiple, seemingly, correct solutions in the form of local minima regions. Through these results, we hope to encourage extending reinforcement learning to more complicated optimization problems and using these novel techniques to efficiently solve traditionally challenging problems in chemistry.
ISSN:1549-9596
1549-960X
DOI:10.1021/acs.jcim.2c00373