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
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?)