Tailored neural networks for learning optimal value functions in MPC [article]

Dieter Teichrib, Moritz Schulze Darup
2021 arXiv   pre-print
Learning-based predictive control is a promising alternative to optimization-based MPC. However, efficiently learning the optimal control policy, the optimal value function, or the Q-function requires suitable function approximators. Often, artificial neural networks (ANN) are considered but choosing a suitable topology is also non-trivial. Against this background, it has recently been shown that tailored ANN allow, in principle, to exactly describe the optimal control policy in linear MPC by
more » ... ploiting its piecewise affine structure. In this paper, we provide a similar result for representing the optimal value function and the Q-function that are both known to be piecewise quadratic for linear MPC.
arXiv:2112.03975v1 fatcat:wexhgbh2kvcjvitbqfwiadvbnq