.png){kind=icon}
Return
Explainable physics-based constraints on reinforcement learning for accelerator optimization
.png){kind=icon}
OA
AI
DOI：10.1088/2632-2153/ae2fa8.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
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.
Journal
M
IF:
0
Papers:
116
Citations:
0
Organization
Cited Papers
Simultaneous optimization of the cavity heat load and trip rates in linacs using a genetic algorithm
OAAI
.png){kind=icon}
OAAIShareSaveShareSaveMachine-Learning Optimized Measurements of Chaotic Dynamical Systems via the Information BottleneckOAAI
OAAIShareSaveShareSaveDiscovering governing equations from data by sparse identification of nonlinear dynamical systemsOAAI
OAAIShareSaveShareSave
View more