ORCID
0000-0003-4162-0276 (Colen), 0000-0002-3475-2871 (Schram)
Document Type
Article
Publication Date
2026
DOI
10.1088/2632-2153/ae2fa8
Publication Title
Machine Learning: Science and Technology
Volume
7
Issue
1
Pages
015005
Abstract
We present a reinforcement learning (RL) framework for optimizing particle accelerator experiments that builds explainable physics-based constraints on agent behavior. The goal is to increase transparency and trust by letting users verify that the agent’s decision-making process incorporates suitable physics. Our algorithm uses a learnable surrogate function for physical observables, such as energy, and uses them to fine-tune how actions are chosen. This surrogate can be represented by a neural network or by an interpretable sparse dictionary model. We test our algorithm on a range of particle accelerator optimization environments designed to emulate the Continuous Electron Beam Accelerator Facility at Jefferson Lab. By examining the mathematical form of the learned constraint function, we are able to confirm the agent has learned to use the established physics of each environment. In addition, we find that the introduction of a physics-based surrogate enables our RL algorithms to reliably converge for difficult high-dimensional accelerator optimization environments.
Rights
© 2026 The Authors
Original content from this work may be used under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) License.
Data Availability
Article states: "The data that support the findings of this study are openly available at the following URL/DOI: https://github.com/jcolen/explainable_constraints. Supplementary Information available at https://doi.org/10.1088/2632-2153/ae2fa8/data1."
Original Publication Citation
Colen, J., Schram, M., Rajput, K., & Kasparian, A. (2026). Explainable physics-based constraints on reinforcement learning for accelerator optimization. Machine Learning: Science and Technology, 7(1), 1-13, Article 015005. https://doi.org/10.1088/2632-2153/ae2fa8
Repository Citation
Colen, J., Schram, M., Rajput, K., & Kasparian, A. (2026). Explainable physics-based constraints on reinforcement learning for accelerator optimization. Machine Learning: Science and Technology, 7(1), 1-13, Article 015005. https://doi.org/10.1088/2632-2153/ae2fa8
Included in
Artificial Intelligence and Robotics Commons, Data Science Commons, Engineering Physics Commons, Theory and Algorithms Commons