mlsanityData to 14 Oct 2026

GoSafe: Globally Optimal Safe Robot Learning

arXiv 2105.13281 ↗First posted 27 May 2021cs.RO cs.LG cs.SYcited by 27

Not on the map. Why?

Abstract (arXiv)

When learning policies for robotic systems from data, safety is a major concern, as violation of safety constraints may cause hardware damage. SafeOpt is an efficient Bayesian optimization (BO) algorithm that can learn policies while guaranteeing safety with high probability. However, its search space is limited to an initially given safe region. We extend this method by exploring outside the initial safe area while still guaranteeing safety with high probability. This is achieved by learning a set of initial conditions from which we can recover safely using a learned backup controller in case of a potential failure. We derive conditions for guaranteed convergence to the global optimum and validate GoSafe in hardware experiments.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 17 of its 33 references that are in the map. First posted on arXiv 27 May 2021.

Builds on

17 of 33 references.

References · 17

  1. 2017Constrained Policy Optimizationcited by 983
  2. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 366
  3. 2017On Kernelized Multi-armed Banditscited by 352
  4. 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 297
  5. 2016Bayesian Optimization with Safety Constraints: Safe and Automatic Parameter Tuning in Roboticscited by 134
  6. 2014Bayesian Optimization with Unknown Constraintscited by 109
  7. 2015Safe Controller Optimization for Quadrotors with Gaussian Processescited by 78
  8. 2016Safe Exploration in Finite Markov Decision Processes with Gaussian Processescited by 75
  9. 2019Safe Exploration for Interactive Machine Learningcited by 51
  10. 2015A General Framework for Constrained Bayesian Optimization using Information-based Searchcited by 50
  11. 2016Safe Learning of Regions of Attraction for Uncertain, Nonlinear Systems with Gaussian Processescited by 39
  12. 2016Automatic LQR Tuning Based on Gaussian Process Global Optimizationcited by 30
5 more
  1. 2019Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimizationcited by 16
  2. 2020Robot Learning with Crash Constraintscited by 15
  3. 2017Deep Kernels for Optimizing Locomotion Controllerscited by 14
  4. 2019A Learnable Safety Measurecited by 7
  5. 2020Excursion Search for Constrained Bayesian Optimization under a Limited Budget of Failurescited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 6; 2024: 13; 2025: 4; 2026: 1.

27 papers.

Sort:

By area:

  1. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
  2. 2024ActSafe: Active Exploration with Safety Constraints for Reinforcement Learningcited by 23
  3. 2022GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systemscited by 17
  4. 2023A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviorscited by 15
  5. 2024On Safety in Safe Bayesian Optimizationcited by 15
  6. 2025Safe exploration in reproducing kernel Hilbert spacescited by 10
  7. 2023Tuning Legged Locomotion Controllers via Safe Bayesian Optimizationcited by 9
  8. 2024PACSBO: Probably approximately correct safe Bayesian optimizationcited by 8
  9. 2024Boundary Exploration for Bayesian Optimization With Unknown Physical Constraintscited by 6
  10. 2025Koopman-Equivariant Gaussian Processescited by 6
  11. 2024Safe Exploration Using Bayesian World Models and Log-Barrier Optimizationcited by 4
  12. 2024Safe Time-Varying Optimization based on Gaussian Processes with Spatio-Temporal Kernelcited by 4
15 more
  1. 2024Towards safe Bayesian optimization with Wiener kernel regressioncited by 4
  2. 2024Safe Bayesian Optimization for the Control of High-Dimensional Embodied Systemscited by 4
  3. 2023Primal-Dual Contextual Bayesian Optimization for Control System Online Optimization with Time-Average Constraintscited by 3
  4. 2023A computationally lightweight safe learning algorithmcited by 3
  5. 2024Local Bayesian Optimization for Controller Tuning with Crash Constraintscited by 3
  6. 2023Machine Learning Meets Advanced Robotic Manipulationcited by 2
  7. 2024Efficiently Computable Safety Bounds for Gaussian Processes in Active Learningcited by 2
  8. 2025Safety and optimality in learning-based control at low computational costcited by 2
  9. 2022Benefits of Monotonicity in Safe Exploration with Gaussian Processescited by 1
  10. 2023Bayesian inference for data-efficient, explainable, and safe robotic motion planning: A reviewcited by 1
  11. 2024Global Safe Sequential Learning via Efficient Knowledge Transfercited by 1
  12. 2024Future Aware Safe Active Learning of Time Varying Systems using Gaussian Processescited by 1
  13. 2024No-Regret Algorithms for Safe Bayesian Optimization with Monotonicity Constraintscited by 1
  14. 2025Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Reviewcited by 1
  15. 2026Safe learning-based control via function-based uncertainty quantificationcited by 1