% 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{Rttgers:1052700,
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-2026-01057},
isbn = {978-3-031-85702-7 (print)},
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 frequentbut
also most debated interventions in the field of rhinology. A
previouslydeveloped tool enhances surgery planning by
physical aspects of respi-ration, i.e., for the first time a
reinforcement learning (RL) algorithm iscombined with
large-scale computational fluid dynamics (CFD) simula-tions
to plan anti-obstructive surgery. In the current study, an
improve-ment of the tool’s predictive capabilities is
investigated for the afore-mentioned types of surgeries by
considering two approaches: (i) trainingof parallel
environments is executed on multiple ranks and the agentsof
each environment share their experience in a pre-defined
interval and(ii) for some of the state-reward combinations
the CFD solver is replacedby a Gaussian process regression
(GPR) model for an improved compu-tational efficiency. It is
found that employing a parallel RL algorithmimproves the
reliability of the surgery planning tool in finding the
globaloptimum. However, parallel training leads to a larger
number of state-reward combinations that need to be computed
by the CFD solver. Thisoverhead is compensated by replacing
some of the computations withthe GPR algorithm, i.e., around
$6\%$ of the computations can be savedwithout significantly
degrading the predictions’ accuracy.
Nevertheless,increasing the number of state-reward
combinations predicted by theGPR algorithm only works to a
certain extent, since this also leads tolarger errors.},
month = {Sep},
date = {2024-09-08},
organization = {International Conference on Parallel
Processing and Applied Mathematics,
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) / SDLFSE - SDL Fluids
$\&$ Solids Engineering (SDLFSE) / HANAMI - Hpc AlliaNce for
Applications and supercoMputing Innovation: the Europe -
Japan collaboration (101136269)},
pid = {G:(DE-HGF)POF4-5111 / G:(DE-Juel-1)SDLFSE /
G:(EU-Grant)101136269},
typ = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
doi = {10.1007/978-3-031-85703-4_6},
url = {https://juser.fz-juelich.de/record/1052700},
}