Explainable physics-based constraints on reinforcement learning for accelerator optimization

doi:10.1088/2632-2153/ae2fa8

Explainable physics-based constraints on reinforcement learning for accelerator optimization

2026-01-09

0

OA

AI

DOI：10.1088/2632-2153/ae2fa8

Original

Original request for help

Save

Abstract

En 中文

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.

Explainable physics-based constraints on reinforcement learning for accelerator optimization

Abstract

Journal

Organization