| Paper |
Title |
Page |
| THPAB191 |
Physics-Enhanced Reinforcement Learning for Optimal Control |
4150 |
| |
- A.N. Ivanov, I.V. Agapov, A. Eichler, S. Tomin
DESY, Hamburg, Germany
|
|
| |
We propose an approach for incorporating accelerator physics models into reinforcement learning agents. The proposed approach is based on the Taylor mapping technique for simulation of the particle dynamics. The resulting computational graph is represented as a polynomial neural network and embedded into the traditional reinforcement learning agents. The application of the model is demonstrated in a nonlinear simulation model of beam transmission. The comparison of the approach with the traditional numerical optimization as well as neural networks based agents demonstrates better convergence of the proposed technique.
|
|
|
Poster THPAB191 [0.846 MB]
|
|
| DOI • |
reference for this paper
※ https://doi.org/10.18429/JACoW-IPAC2021-THPAB191
|
|
| About • |
paper received ※ 11 May 2021 paper accepted ※ 29 July 2021 issue date ※ 24 August 2021 |
|
| Export • |
reference for this paper using
※ BibTeX,
※ LaTeX,
※ Text/Word,
※ RIS,
※ EndNote (xml)
|
|
| |