mlsanityData to 14 Oct 2026

Task-Oriented Koopman-Based Control with Contrastive Encoder

arXiv 2309.16077 ↗First posted 28 Sep 2023cs.RO cs.LG cs.SYcited by 8

Not on the map. Why?

Abstract (arXiv)

We present task-oriented Koopman-based control that utilizes end-to-end reinforcement learning and contrastive encoder to simultaneously learn the Koopman latent embedding, operator, and associated linear controller within an iterative loop. By prioritizing the task cost as the main objective for controller learning, we reduce the reliance of controller design on a well-identified model, which, for the first time to the best of our knowledge, extends Koopman control from low to high-dimensional, complex nonlinear systems, including pixel-based tasks and a real robot with lidar observations. Code and videos are available hrefhttps://sites.google.com/view/kpmlilatsupp/here.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 23 of its 40 references that are in the map. First posted on arXiv 28 Sep 2023.

Builds on

23 of 40 references.

References · 23

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  4. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  5. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  6. 2020Mastering Atari with Discrete World Modelscited by 1,007
  7. 2018DeepMind Control Suitecited by 956
  8. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 760
  9. 2017Deep learning for universal linear embeddings of nonlinear dynamicscited by 494
  10. 2016Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive controlcited by 140
  11. 2014Dynamic mode decomposition with controlcited by 129
  12. 2021Safe Nonlinear Control Using Robust Neural Lyapunov-Barrier Functionscited by 94
11 more
  1. 2017Data-driven discovery of Koopman eigenfunctions for controlcited by 64
  2. 2019Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysiscited by 40
  3. 2021Contrasting Contrastive Self-Supervised Representation Learning Pipelinescited by 37
  4. 2018Optimal construction of Koopman eigenfunctions for prediction and controlcited by 35
  5. 2020Deep Learning of Koopman Representation for Controlcited by 26
  6. 2022Deep Koopman Operator with Control for Nonlinear Systemscited by 25
  7. 2017Model-Based Control Using Koopman Operatorscited by 14
  8. 2023ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representationscited by 10
  9. 2020DeepKoCo: Efficient latent planning with a task-relevant Koopman representationcited by 5
  10. 2017An Optimal Control Formulation of Pulse-Based Control Using Koopman Operatorcited by 3
  11. 2022Data-Efficient Model Learning for Control with Jacobian-Regularized Dynamic-Mode Decomposition}cited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 3; 2026: 2.

8 papers.

  1. 2025Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systemscited by 7
  2. 2025Intelligent Sensing-to-Action for Robust Autonomy at the Edge: Opportunities and Challengescited by 5
  3. 2024RoboKoop: Efficient Control Conditioned Representations from Visual Input in Robotics using Koopman Operatorcited by 4
  4. 2026Koopman Dreamer: Spectrally Constrained Latent Dynamics for Stable World-Model Imaginationcited by 4
  5. 2023Course Correcting Koopman Representationscited by 2
  6. 2024Imitation Learning with Limited Actions via Diffusion Planners and Deep Koopman Controllerscited by 2
  7. 2026Operator-on-F complements value-equivalence: a planning-time diagnostic for latent world modelscited by 2
  8. 2025SALSA-RL: Stability Analysis in the Latent Space of Actions for Reinforcement Learningcited by 0