mlsanityData to 14 Oct 2026

PACSBO: Probably approximately correct safe Bayesian optimization

arXiv 2409.01163 ↗First posted 2 Sep 2024cs.LG cs.SY eess.SYcited by 8

Not on the map. Why?

Abstract (arXiv)

Safe Bayesian optimization (BO) algorithms promise to find optimal control policies without knowing the system dynamics while at the same time guaranteeing safety with high probability. In exchange for those guarantees, popular algorithms require a smoothness assumption: a known upper bound on a norm in a reproducing kernel Hilbert space (RKHS). The RKHS is a potentially infinite-dimensional space, and it is unclear how to, in practice, obtain an upper bound of an unknown function in its corresponding RKHS. In response, we propose an algorithm that estimates an upper bound on the RKHS norm of an unknown function from data and investigate its theoretical properties. Moreover, akin to Lipschitz-based methods, we treat the RKHS norm as a local rather than a global object, and thus reduce conservatism. Integrating the RKHS norm estimation and the local interpretation of the RKHS norm into a safe BO algorithm yields PACSBO, an algorithm for probably approximately correct safe Bayesian optimization, for which we provide numerical and hardware experiments that demonstrate its applicability and benefits over popular safe BO algorithms.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 17 of its 30 references that are in the map. First posted on arXiv 2 Sep 2024.

Builds on

17 of 30 references.

References · 17

  1. 2015Continuous control with deep reinforcement learningcited by 3,407
  2. 2018A Tutorial on Bayesian Optimizationcited by 744
  3. 2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 371
  4. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
  5. 2017On Kernelized Multi-armed Banditscited by 352
  6. 2016Bayesian Optimization with Safety Constraints: Safe and Automatic Parameter Tuning in Roboticscited by 134
  7. 2018Stagewise Safe Bayesian Optimization with Gaussian Processescited by 79
  8. 2021Practical and Rigorous Uncertainty Bounds for Gaussian Process Regressioncited by 49
  9. 2016Automatic LQR Tuning Based on Gaussian Process Global Optimizationcited by 30
  10. 2021GoSafe: Globally Optimal Safe Robot Learningcited by 27
  11. 2022GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systemscited by 17
  12. 2024On Safety in Safe Bayesian Optimizationcited by 15
5 more
  1. 2017Deep Kernels for Optimizing Locomotion Controllerscited by 14
  2. 2021Robust Uncertainty Bounds in Reproducing Kernel Hilbert Spaces: A Convex Optimization Approachcited by 14
  3. 2023Automatic nonlinear MPC approximation with closed-loop guaranteescited by 12
  4. 2020Learning-based Symbolic Abstractions for Nonlinear Control Systemscited by 11
  5. 2016Lazily Adapted Constant Kinky Inference for Nonparametric Regression and Model-Reference Adaptive Controlcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 3.

8 papers.

  1. 2025Safe exploration in reproducing kernel Hilbert spacescited by 10
  2. 2025Optimal kernel regression bounds under energy-bounded noisecited by 4
  3. 2025Safety and optimality in learning-based control at low computational costcited by 2
  4. 2025Safe Bayesian optimization across noise models via scenario programmingcited by 1
  5. 2026Safe learning-based control via function-based uncertainty quantificationcited by 1
  6. 2025Towards safe control parameter tuning in distributed multi-agent systemscited by 0
  7. 2026Asynchronous Cooperative Online Learning for Multi-Robot Control under Computational Delayscited by 0
  8. 2026Event-triggered Control and Online Learning for Networked Systems under Computational Delayscited by 0