Economic Model Predictive Control with Policy-Guided Terminal Ingredients

arXiv:2609.02628 2026 Dynamics 1 ideas extracted · analyzed Sep 3, 2026

What the math gives to ML

The paper replaces steady-state terminal ingredients in MPC with a rollout of a known, possibly suboptimal policy. A terminal center is generated by the guiding policy, while the terminal cost penalizes deviation from that center and a terminal set ensures that the guiding policy can continue feasibly. The transferable mechanism is a policy-relative trust region for finite-horizon optimization: rather than forcing an optimizer toward a fixed target, constrain its endpoint to remain near a dynamically generated baseline trajectory. A practical neural-network use is a lookahead optimizer that searches over several parameter updates while using a cheap baseline optimizer as the terminal policy and fallback controller.

Ideas from this paper

Unverified 2026

Policy-Guided Terminal Trust Region for Optimizers

Treat neural-network parameters as the state of a controlled dynamical system and optimize a short sequence of parameter updates instead of committing immediately to the next optimizer step. A cheap guiding optimizer, such as Adam or SGD, is rolled out to produce a moving terminal center; the lookahead optimizer is penalized or constrained when its endpoint leaves a neighborhood of that center. This transfers the paper's policy-relative feasibility and performance idea without requiring a…

Useful7/10
Difficulty7/10
Novelty7/10
Paper: Economic Model Predictive Control with Policy-Guided Terminal Ingredients arXiv:2609.02628