mlsanityData to 14 Oct 2026

Safe Learning and Optimization Techniques: Towards a Survey of the State of the Art

arXiv 2101.09505 ↗First posted 23 Jan 2021cs.LG cs.NE math.OCcited by 16

Not on the map. Why?

Abstract (arXiv)

Safe learning and optimization deals with learning and optimization problems that avoid, as much as possible, the evaluation of non-safe input points, which are solutions, policies, or strategies that cause an irrecoverable loss (e.g., breakage of a machine or equipment, or life threat). Although a comprehensive survey of safe reinforcement learning algorithms was published in 2015, a number of new algorithms have been proposed thereafter, and related works in active learning and in optimization were not considered. This paper reviews those algorithms from a number of domains including reinforcement learning, Gaussian process regression and classification, evolutionary algorithms, and active learning. We provide the fundamental concepts on which the reviewed algorithms are based and a characterization of the individual algorithms. We conclude by explaining how the algorithms are connected and suggestions for future research.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 7 of its 38 references that are in the map. First posted on arXiv 23 Jan 2021.

Builds on

7 of 38 references.

References · 7

  1. 2018A Tutorial on Bayesian Optimizationcited by 744
  2. 2016Bayesian Optimization with Safety Constraints: Safe and Automatic Parameter Tuning in Roboticscited by 134
  3. 2018Stagewise Safe Bayesian Optimization with Gaussian Processescited by 79
  4. 2015Safe Controller Optimization for Quadrotors with Gaussian Processescited by 78
  5. 2016Safe Exploration in Finite Markov Decision Processes with Gaussian Processescited by 75
  6. 2019Safe Exploration for Interactive Machine Learningcited by 51
  7. 2019Efficient and Safe Exploration in Deterministic Markov Decision Processes with Unknown Transition Modelscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 4; 2023: 2; 2024: 4; 2025: 2; 2026: 1.

16 papers.

Sort:

By area:

  1. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
  2. 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 181
  3. 2024A Survey of Constraint Formulations in Safe Reinforcement Learningcited by 44
  4. 2021Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processescited by 17
  5. 2024On Safety in Safe Bayesian Optimizationcited by 15
  6. 2022Falsification of Learning-Based Controllers through Multi-Fidelity Bayesian Optimizationcited by 4
  7. 2026Safe Continual Reinforcement Learning Methods for Nonstationary Environments. Towards a Survey of the State of the Artcited by 2
  8. 2021Heterogeneous Objectives: State-of-the-Art and Future Researchcited by 1
  9. 2023Modeling Risk in Reinforcement Learning: A Literature Mappingcited by 1
  10. 2024Physics-informed RL for Maximal Safety Probability Estimationcited by 1
  11. 2025Exchange Policy Optimization Algorithm for Semi-Infinite Safe Reinforcement Learningcited by 1
  12. 2022Are Evolutionary Algorithms Safe Optimizers?cited by 0
4 more
  1. 2022Learning Disturbances Online for Risk-Aware Control: Risk-Aware Flight with Less Than One Minute of Datacited by 0
  2. 2023Probabilistic Counterexample Guidance for Safer Reinforcement Learning (Extended Version)cited by 0
  3. 2024Optimizing Falsification for Learning-Based Control Systems: A Multi-Fidelity Bayesian Approachcited by 0
  4. 2025Counterfactual Credit Guided Bayesian Optimizationcited by 0