AI & ML
Policy-Conditioned Koopman Representations for Parameterized Closed-Loop Systems
arXiv eess.SY0 views
arXiv:2611.18451v1 Announce Type: new Abstract: Predicting the response of a nonlinear system across different feedback controllers requires a model that captures how the closed-loop dynamics change with the controller parameters. In a finite-dimensional Koopman model, these changes may affect both the latent dynamics and the observable coordinates used to represent them. In this paper, we propose a policy-conditioned Koopman representation framework to address this problem. This framework allows a single learned model to predict a family of closed-loop trajectories without retraining for each controller. We test the framework on four nonlinear prediction benchmarks, where the model stays below a 15% error threshold on every system, while each baseline exceeds it on at least one. As an example application, the resulting surrogate supports one-shot feedback-parameter selection: an optimization at the initial state selects a controller that then operates with fixed parameters and ongoing state feedback. On nonlinear control benchmarks including MuJoCo, the selected controllers stabilize every system with 3 to 97 times less online computation than nonlinear model predictive control. These results demonstrate how policy-dependent coordinates can support both prediction across closed-loop systems and controller selection without repeated online trajectory optimization.
Source:https://arxiv.org/abs/2611.18451PreviousGrid-Forming AI Data Centers: Coordinated Grid Support Control from IT Loads and Energy StorageNextEPIGRIDS: Documentation and Validation of Seven Open Synthetic Transmission Grid Cases
Related posts
Building AI that can work across the enterprise
0MIT Technology Review

The Download: testing tech promises and searching for cognitive immortality
0MIT Technology Review

The Nvidia scandal isn’t slowing down
0The Verge

Google Maps can now create trip itineraries for you
0The Verge

Audible is trying to make it easier to find audiobooks you’ll actually like
0The Verge
Bedrock Energy raises $24M to build more AI-enabled geothermal drill rigs for enterprise buildings
0TechCrunch