mlsanityData to 7 Oct 2026

GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems

arXiv 2201.09562 ↗First posted 24 Jan 2022cs.LG cs.SY eess.SYcited by 17

Not on the map. Why?

Abstract (arXiv)

Learning optimal control policies directly on physical systems is challenging since even a single failure can lead to costly hardware damage. Most existing model-free learning methods that guarantee safety, i.e., no failures, during exploration are limited to local optima. A notable exception is the GoSafe algorithm, which, unfortunately, cannot handle high-dimensional systems and hence cannot be applied to most real-world dynamical systems. This work proposes GoSafeOpt as the first algorithm that can safely discover globally optimal policies for high-dimensional systems while giving safety and optimality guarantees. We demonstrate the superiority of GoSafeOpt over competing model-free safe learning methods on a robot arm that would be prohibitive for GoSafe.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 32 of its 62 references that are in the map. First posted on arXiv 24 Jan 2022.

Builds on

32 of 62 references.

References · 32

  1. 2015Continuous control with deep reinforcement learningcited by 3,279
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  3. 2015Trust Region Policy Optimizationcited by 2,503
  4. 2017Constrained Policy Optimizationcited by 928
  5. 2015End-to-End Training of Deep Visuomotor Policiescited by 847
  6. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
  7. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 494
  8. 2019Learning agile and dynamic motor skills for legged robotscited by 402
  9. 2017On Kernelized Multi-armed Banditscited by 348
  10. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  11. 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 278
  12. 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 256
20 more
  1. 2016Bayesian Optimization with Safety Constraints: Safe and Automatic Parameter Tuning in Roboticscited by 134
  2. 2014Bayesian Optimization with Unknown Constraintscited by 109
  3. 2020Learning to be Safe: Deep RL with a Safety Criticcited by 109
  4. 2018A predictive safety filter for learning-based control of constrained nonlinear dynamical systemscited by 91
  5. 2018Stagewise Safe Bayesian Optimization with Gaussian Processescited by 79
  6. 2015Safe Controller Optimization for Quadrotors with Gaussian Processescited by 77
  7. 2019Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspacescited by 73
  8. 2021Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learningcited by 73
  9. 2020Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Compositioncited by 71
  10. 2015A General Framework for Constrained Bayesian Optimization using Information-based Searchcited by 50
  11. 2019No-Regret Bayesian Optimization with Unknown Hyperparameterscited by 50
  12. 2021Practical and Rigorous Uncertainty Bounds for Gaussian Process Regressioncited by 49
  13. 2016Automatic LQR Tuning Based on Gaussian Process Global Optimizationcited by 29
  14. 2021GoSafe: Globally Optimal Safe Robot Learningcited by 27
  15. 2019Safe Contextual Bayesian Optimization for Sustainable Room Temperature PID Control Tuningcited by 24
  16. 2019Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimizationcited by 16
  17. 2020Robot Learning with Crash Constraintscited by 15
  18. 2017Deep Kernels for Optimizing Locomotion Controllerscited by 14
  19. 2021Safe and Efficient Model-free Adaptive Control via Bayesian Optimizationcited by 10
  20. 2019A Learnable Safety Measurecited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 7; 2025: 5; 2026: 2.

17 papers.

Sort:

By area:

  1. 2024MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximizationcited by 30
  2. 2024ActSafe: Active Exploration with Safety Constraints for Reinforcement Learningcited by 22
  3. 2022Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interactioncited by 15
  4. 2024On Safety in Safe Bayesian Optimizationcited by 15
  5. 2024Safe Reinforcement Learning on the Constraint Manifold: Theory and Applicationscited by 12
  6. 2025Safe exploration in reproducing kernel Hilbert spacescited by 10
  7. 2023Tuning Legged Locomotion Controllers via Safe Bayesian Optimizationcited by 8
  8. 2024PACSBO: Probably approximately correct safe Bayesian optimizationcited by 8
  9. 2026Safe Exploration via Policy Priorscited by 6
  10. 2024Safe Exploration Using Bayesian World Models and Log-Barrier Optimizationcited by 4
  11. 2023A computationally lightweight safe learning algorithmcited by 3
  12. 2025Safety and optimality in learning-based control at low computational costcited by 2
5 more
  1. 2024No-Regret Algorithms for Safe Bayesian Optimization with Monotonicity Constraintscited by 1
  2. 2025Safe Bayesian optimization across noise models via scenario programmingcited by 1
  3. 2025Safely Learning Controlled Stochastic Dynamicscited by 0
  4. 2025Simulation Priors for Data-Efficient Deep Learningcited by 0
  5. 2026Foundations of Reinforcement Learning and Control:Connections and New Perspectivescited by 0