AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Learning Koopman Representations with Controllability Guarantees

Keyan Miao, Han Wang, Xuda Ding, Konstantinos Gatsis, Andreas Krause, Antonis Papachristodoulou

ICLR 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Latent-space control and planning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
enforce controllability via canonical parameterization of Koopman matricesDKO · Mountain Car (1% data)prediction MSE: 0.0200 -> 0.0032Improved
enforce controllabilityDKO · Pendulum (1% data)prediction MSE: 1.5347 -> 0.3747Improved
enforce controllabilityDKO · Cartpole (1% data)prediction MSE: 0.1306 -> 0.0095Improved
enforce controllability with abundant data (50-100%)DKO · Mountain Car / Pendulum / Cartpoleprediction MSENo clear effect
Koopman controllable model instead of plain MLP at 1% dataMLP · Pendulum (1% data)prediction MSE: 1.1778 -> 0.3747Improved
use controllable model in MPC with 5% dataDKO · Mountain Car (5% data)MPC input cost: 297.51 -> 165.21Improved
use controllable model in MPC with 10% dataDKO · Pendulum swing-up (10% data)MPC input cost: 239.2 -> 43.50Improved
use controllable model in MPC with scarce dataDKO · Mountain Car 1%, Pendulum 5%, Cartpole 30%MPC task completionImproved
controllable model on multi-input GRNDKO · GRN 6-dimtest MSE: 3.0 × 10−4 -> 1.0 × 10−4Improved
controllable model on GRN controlDKO · GRN setpoint 6MPC input cost: 89.98 -> 80.96Improved
enforce controllability priorDKO · Mountain Car, Pendulum, Cartpoletraining convergenceImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy