AI News HubLIVE
原文

Robust Koopman Control Barrier Filters for Safe Actor-Critic Reinforcement Learning

This paper proposes Robust Koopman-CBF SAC, a safety-filtered actor-critic framework that learns a Koopman predictor from data, constructs affine CBF constraints in a lifted space, and enforces them via a quadratic-program safety layer with robustness to approximation error. It achieves zero constraint violations on CartPole benchmarks while matching or exceeding unconstrained SAC returns, but reveals limitations on high-dimensional tasks.

Article intelligence

EngineersAdvanced

Key points

  • Proposes Robust Koopman-CBF SAC, combining data-driven Koopman prediction with CBF safety filters.
  • Enforces affine CBF constraints via a quadratic-program safety layer, with robustness margins from projection residuals.
  • Achieves zero constraint violations on CartPole, matching or exceeding unconstrained SAC performance.
  • Reduces violations on high-dimensional Safety Gym tasks, but highlights limitations of first-order velocity barriers and linear EDMD models.

Why it matters

This matters because proposes Robust Koopman-CBF SAC, combining data-driven Koopman prediction with CBF safety filters.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.26452] Robust Koopman Control Barrier Filters for Safe Actor-Critic Reinforcement Learning

[Submitted on 26 May 2026]

Title:Robust Koopman Control Barrier Filters for Safe Actor-Critic Reinforcement Learning

View a PDF of the paper titled Robust Koopman Control Barrier Filters for Safe Actor-Critic Reinforcement Learning, by Dhruv S. Kushwaha and 1 other authors

View PDF HTML (experimental)

Abstract:Safe reinforcement learning (RL) for robotic systems requires policies that improve task performance while satisfying state and input constraints during both training and deployment. Control barrier functions (CBFs) provide a principled mechanism for enforcing forward invariance through minimally invasive safety filters, but their use in model-free RL is limited by the need for accurate dynamics and hand-designed barrier certificates. We propose Robust Koopman-CBF SAC, a safety-filtered actor--critic framework that learns a finite-dimensional Koopman predictor from data, constructs affine CBF constraints in the lifted space, and enforces them through a quadratic-program safety layer. To account for finite-dimensional Koopman approximation error, the CBF condition is tightened using a projected residual margin estimated from held-out rollout data. The critic is trained on the executed safe action, while the actor is regularized toward the Koopman-CBF feasible set, reducing dependence on the filter over training. Across safe-control benchmarks, the method achieves zero constraint violations on CartPole stabilization and tracking while matching or exceeding unconstrained SAC returns. On high-dimensional Safety Gymnasium locomotion tasks, the method reduces violations in some settings but also exposes important limitations of first-order velocity barriers and linear EDMD models, motivating high-order and multi-step Koopman-CBF extensions. These results suggest that robust Koopman-CBF filters are a promising bridge between model-free RL and certifiable safety, while clarifying the structural conditions under which such filters remain effective. All code is available at \href{this https URL}{Github Repository}.

Comments: 17 pages, 7 figures

Subjects:

Robotics (cs.RO); Machine Learning (cs.LG); Systems and Control (eess.SY)

MSC classes: 93E99

ACM classes: A.1; I.2

Cite as: arXiv:2605.26452 [cs.RO]

(or arXiv:2605.26452v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2605.26452

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Dhruv Kushwaha [view email] [v1] Tue, 26 May 2026 02:02:40 UTC (1,471 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Robust Koopman Control Barrier Filters for Safe Actor-Critic Reinforcement Learning, by Dhruv S. Kushwaha and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.RO

new | recent | 2026-05

Change to browse by:

cs cs.LG cs.SY eess eess.SY

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)