% 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”.

@ARTICLE{Mayfrank:1038126,
      author       = {Mayfrank, Daniel and Ahn, Na Young and Mitsos, Alexander
                      and Dahmen, Manuel},
      title        = {{T}ask-optimal data-driven surrogate models for e{NMPC} via
                      differentiable simulation and optimization},
      publisher    = {arXiv},
      reportid     = {FZJ-2025-01173},
      year         = {2024},
      abstract     = {We present a method for end-to-end learning of Koopman
                      surrogate models for optimal performance in a specific
                      control task. In contrast to previous contributions that
                      employ standard reinforcement learning (RL) algorithms, we
                      use a training algorithm that exploits the potential
                      differentiability of environments based on mechanistic
                      simulation models to aid the policy optimization. We
                      evaluate the performance of our method by comparing it to
                      that of other controller type and training algorithm
                      combinations on an existing economic nonlinear model
                      predictive control (eNMPC) case study of a continuous
                      stirred-tank reactor (CSTR) model. Compared to the benchmark
                      methods, our method produces similar economic performance
                      but causes considerably fewer and less severe constraint
                      violations. Thus, for this case study, our method
                      outperforms the others and offers a promising path toward
                      more performant controllers that employ dynamic surrogate
                      models.},
      keywords     = {Machine Learning (cs.LG) (Other) / Optimization and Control
                      (math.OC) (Other) / FOS: Computer and information sciences
                      (Other) / FOS: Mathematics (Other)},
      cin          = {ICE-1},
      cid          = {I:(DE-Juel1)ICE-1-20170217},
      pnm          = {1121 - Digitalization and Systems Technology for
                      Flexibility Solutions (POF4-112) / HDS LEE - Helmholtz
                      School for Data Science in Life, Earth and Energy (HDS LEE)
                      (HDS-LEE-20190612)},
      pid          = {G:(DE-HGF)POF4-1121 / G:(DE-Juel1)HDS-LEE-20190612},
      typ          = {PUB:(DE-HGF)25},
      doi          = {10.48550/ARXIV.2403.14425},
      url          = {https://juser.fz-juelich.de/record/1038126},
}