guest ::
| Home > Publications database > Task-optimal data-driven surrogate models for eNMPC via differentiable simulation and optimization |
| Home > Publications database > Task-optimal data-driven surrogate models for eNMPC via differentiable simulation and optimization |
| Preprint | FZJ-2025-01173 |
; ; ;
2024
arXiv
This record in other databases:
Please use a persistent id in citations: doi:10.48550/ARXIV.2403.14425
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.
Keyword(s): Machine Learning (cs.LG) ; Optimization and Control (math.OC) ; FOS: Computer and information sciences ; FOS: Mathematics
|
The record appears in these collections: |