% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@INPROCEEDINGS{Hirlaender:607325,
author = {Hirlaender, Simon and Pochaba, Sabrina and Lamminger, Lukas
and Santamaria Garcia, Andrea and Xu, Chenran and Kaiser,
Jan and Eichler, Annika and Kain, Verena},
title = {{D}eep {M}eta {R}einforcement {L}earning for {R}apid
{A}daptation {I}n {L}inear {M}arkov {D}ecision {P}rocesses:
{A}pplications to {CERN}’s {AWAKE} {P}roject; 1st ed.
2024},
volume = {1458},
address = {Cham},
publisher = {Springer Nature Switzerland},
reportid = {PUBDB-2024-01836},
isbn = {978-3-031-65992-8},
series = {Advances in Intelligent Systems and Computing},
pages = {175 - 183},
year = {2024},
note = {Missing Journal: = 2194-5365 (import from CrossRef Book
Series, Journals: bib-pubdb1.desy.de)},
comment = {[Ebook] Combining, Modelling and Analyzing Imprecision,
Randomness and Dependence / Ansari, Jonathan ; Fuchs,
Sebastian ; Trutschnig, Wolfgang ; Lubiano, María Asunción
; Gil, María Ángeles ; Grzegorzewski, Przemyslaw ;
Hryniewicz, Olgierd 1st ed. 2024, Cham : Springer Nature
Switzerland, 2024,},
booktitle = {[Ebook] Combining, Modelling and
Analyzing Imprecision, Randomness and
Dependence / Ansari, Jonathan ; Fuchs,
Sebastian ; Trutschnig, Wolfgang ;
Lubiano, María Asunción ; Gil, María
Ángeles ; Grzegorzewski, Przemyslaw ;
Hryniewicz, Olgierd 1st ed. 2024, Cham
: Springer Nature Switzerland, 2024,},
abstract = {Real-world applications of reinforcement learning (RL) face
challenges such as the need for numerous interactions and
achieving stable training under dynamic conditions. Meta-RL
emerges as a solution, particularly in environments where
simulations cannot perfectly mimic real-world conditions.
This study demonstrates Meta-RL’s potential in the
CERN’s AWAKE project, focusing on the electron line’s
control. By incorporating Model-Agnostic Meta-Learning
(MAML), we showcase how Meta-RL facilitates rapid adaptation
to environmental changes with minimal interaction steps. Our
findings indicate Meta-RL’s efficacy in managing Partially
Observable Markov Decision Processes (POMDPs) with evolving
hidden parameters, underlining its significance in
high-dimensional control challenges prevalent in particle
physics experiments and beyond.},
month = {Sep},
date = {2024-09-03},
organization = {11th International Conference on Soft
Methods in Probability and Statistics,
Salzburg (Austria), 3 Sep 2024 - 6 Sep
2024},
cin = {MSK / KIT / CERN},
cid = {I:(DE-H253)MSK-20120731 / I:(DE-H253)KIT-20130928 /
I:(DE-H253)CERN-20181204},
pnm = {621 - Accelerator Research and Development (POF4-621) /
InternLabs-0011 - HIR3X - Helmholtz International Laboratory
on Reliability, Repetition, Results at the most advanced
X-ray Sources $(2020_InternLabs-0011)$},
pid = {G:(DE-HGF)POF4-621 / $G:(DE-HGF)2020_InternLabs-0011$},
experiment = {EXP:(DE-H253)ARES-20200101},
typ = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
doi = {10.1007/978-3-031-65993-5_21},
url = {https://bib-pubdb1.desy.de/record/607325},
}