The Joint Accelerator Conferences Website (JACoW) is an international collaboration that publishes the proceedings of accelerator conferences held around the world.
@inproceedings{ivanov:ipac2021-thpab191,
author = {A.N. Ivanov and I.V. Agapov and A. Eichler and S. Tomin},
title = {{Physics-Enhanced Reinforcement Learning for Optimal Control}},
booktitle = {Proc. IPAC'21},
pages = {4150--4152},
eid = {THPAB191},
language = {english},
keywords = {network, lattice, controls, simulation, alignment},
venue = {Campinas, SP, Brazil},
series = {International Particle Accelerator Conference},
number = {12},
publisher = {JACoW Publishing, Geneva, Switzerland},
month = {08},
year = {2021},
issn = {2673-5490},
isbn = {978-3-95450-214-1},
doi = {10.18429/JACoW-IPAC2021-THPAB191},
url = {https://jacow.org/ipac2021/papers/thpab191.pdf},
note = {https://doi.org/10.18429/JACoW-IPAC2021-THPAB191},
abstract = {{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.}},
}