% 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”.
@INBOOK{Rttgers:1038857,
author = {Rüttgers, Mario and Hübenthal, Fabian and Tsubokura,
Makoto and Lintermann, Andreas},
title = {{P}arallel {R}einforcement {L}earning and {G}aussian
{P}rocess {R}egression for {I}mproved {P}hysics-{B}ased
{N}asal {S}urgery {P}lanning},
volume = {15581},
address = {Cham},
publisher = {Springer Nature Switzerland},
reportid = {FZJ-2025-01673},
isbn = {978-3-031-85702-7 (print), 978-3-031-85703-4 (electronic)},
series = {Lecture Notes in Computer Science},
pages = {79 - 96},
year = {2025},
comment = {Parallel Processing and Applied Mathematics},
booktitle = {Parallel Processing and Applied
Mathematics},
abstract = {Septoplasty and turbinectomy are among the most frequent
but also most debated interventions in the field of
rhinology. A previously developed tool enhances surgery
planning by physical aspects of respiration, i.e., for the
first time a reinforcement learning (RL) algorithm is
combined with large-scale computational fluid dynamics (CFD)
simulations to plan anti-obstructive surgery. In the current
study, an improvement of the tool’s predictive
capabilities is investigated for the aforementioned types of
surgeries by considering two approaches: (i) training of
parallel environments is executed on multiple ranks and the
agents of each environment share their experience in a
pre-defined interval and (ii) for some of the state-reward
combinations the CFD solver is replaced by a Gaussian
process regression (GPR) model for an improved computational
efficiency. It is found that employing a parallel RL
algorithm improves the reliability of the surgery planning
tool in finding the global optimum. However, parallel
training leads to a larger number of state-reward
combinations that need to be computed by the CFD solver.
This overhead is compensated by replacing some of the
computations with the GPR algorithm, i.e., around $6\%$ of
the computations can be saved without significantly
degrading the predictions’ accuracy. Nevertheless,
increasing the number of state-reward combinations predicted
by the GPR algorithm only works to a certain extent, since
this also leads to larger errors.},
month = {Sep},
date = {2024-09-08},
organization = {Parallel Processing and Applied
Mathematics 2024, Ostrava (Czech
Republic), 8 Sep 2024 - 11 Sep 2024},
cin = {JSC},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
(SDLs) and Research Groups (POF4-511) / HANAMI - Hpc
AlliaNce for Applications and supercoMputing Innovation: the
Europe - Japan collaboration (101136269)},
pid = {G:(DE-HGF)POF4-5111 / G:(EU-Grant)101136269},
typ = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
url = {https://juser.fz-juelich.de/record/1038857},
}