%0 Conference Paper
%A Hirlaender, Simon
%A Pochaba, Sabrina
%A Lamminger, Lukas
%A Santamaria Garcia, Andrea
%A Xu, Chenran
%A Kaiser, Jan
%A Eichler, Annika
%A Kain, Verena
%T Deep Meta Reinforcement Learning for Rapid Adaptation In Linear Markov Decision Processes: Applications to CERN’s AWAKE Project; 1st ed. 2024
%V 1458
%C Cham
%I Springer Nature Switzerland
%M PUBDB-2024-01836
%@ 978-3-031-65992-8
%B Advances in Intelligent Systems and Computing
%P 175 - 183
%D 2024
%Z Missing Journal: = 2194-5365 (import from CrossRef Book Series, Journals: bib-pubdb1.desy.de)
%< [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,
%X 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.
%B 11th International Conference on Soft Methods in Probability and Statistics
%C 3 Sep 2024 - 6 Sep 2024, Salzburg (Austria)
Y2 3 Sep 2024 - 6 Sep 2024
M2 Salzburg, Austria
%F PUB:(DE-HGF)8 ; PUB:(DE-HGF)7
%9 Contribution to a conference proceedingsContribution to a book
%R 10.1007/978-3-031-65993-5_21
%U https://bib-pubdb1.desy.de/record/607325