Rollout Then Optimize: A One-Step Newton Refinement of Learned Policies for Nonlinear Model Predictive Control

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ghezzi, Andrea, Reiter, Rudolf, Baumgärtner, Katrin, Bemporad, Alberto, Diehl, Moritz
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914462064181248
author Ghezzi, Andrea
Reiter, Rudolf
Baumgärtner, Katrin
Bemporad, Alberto
Diehl, Moritz
author_facet Ghezzi, Andrea
Reiter, Rudolf
Baumgärtner, Katrin
Bemporad, Alberto
Diehl, Moritz
contents We propose a computationally efficient rollout-then-optimize method to improve a learned control policy at deployment time. A learned policy provides a nominal trajectory, which is refined online by a single Newton step implemented via a Riccati recursion within a model predictive control (MPC) scheme. This refinement combines model knowledge with the learned policy at minimal additional computational cost. We establish bounds on the approximation error of the learned policy relative to the MPC policy and show that one Newton step reduces the suboptimality of the learned rollout quadratically in the policy approximation error. The proposed controller is validated in simulation on a constrained trajectory-tracking task for a quadcopter with nonlinear dynamics. Results highlight that the Newton step significantly improves the learned policy, achieving performance close to a fully converged MPC solution while requiring roughly half of the computational time. The code is available at https://github.com/aghezz1/rl-riccati.
format Preprint
id arxiv_https___arxiv_org_abs_2504_02710
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Rollout Then Optimize: A One-Step Newton Refinement of Learned Policies for Nonlinear Model Predictive Control
Ghezzi, Andrea
Reiter, Rudolf
Baumgärtner, Katrin
Bemporad, Alberto
Diehl, Moritz
Optimization and Control
We propose a computationally efficient rollout-then-optimize method to improve a learned control policy at deployment time. A learned policy provides a nominal trajectory, which is refined online by a single Newton step implemented via a Riccati recursion within a model predictive control (MPC) scheme. This refinement combines model knowledge with the learned policy at minimal additional computational cost. We establish bounds on the approximation error of the learned policy relative to the MPC policy and show that one Newton step reduces the suboptimality of the learned rollout quadratically in the policy approximation error. The proposed controller is validated in simulation on a constrained trajectory-tracking task for a quadcopter with nonlinear dynamics. Results highlight that the Newton step significantly improves the learned policy, achieving performance close to a fully converged MPC solution while requiring roughly half of the computational time. The code is available at https://github.com/aghezz1/rl-riccati.
title Rollout Then Optimize: A One-Step Newton Refinement of Learned Policies for Nonlinear Model Predictive Control
topic Optimization and Control
url https://arxiv.org/abs/2504.02710