mlsanityData to 7 Oct 2026

Learning-based Model Predictive Control for Safe Exploration

arXiv 1803.08287 ↗First posted 22 Mar 2018eess.SY cs.AI cs.LGcited by 116

Not on the map. Why?

Abstract (arXiv)

Learning-based methods have been successful in solving complex control tasks without significant prior knowledge about the system. However, these methods typically do not provide any safety guarantees, which prevents their use in safety-critical, real-world applications. In this paper, we present a learning-based model predictive control scheme that can provide provable high-probability safety guarantees. To this end, we exploit regularity assumptions on the dynamics in terms of a Gaussian process prior to construct provably accurate confidence intervals on predicted trajectories. Unlike previous approaches, we do not assume that model uncertainties are independent. Based on these predictions, we guarantee that trajectories satisfy safety constraints. Moreover, we use a terminal set constraint to recursively guarantee the existence of safe control actions at every iteration. In our experiments, we show that the resulting algorithm can be used to safely and efficiently explore and learn about dynamic systems.

Key facts. Cited by 116 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 31; 2022: 27; 2023: 18; 2024: 18; 2025: 10; 2026: 12.

116 papers.

Sort:

By area:

  1. 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 169
  2. 2021Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPscited by 78
  3. 2025SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learningcited by 69
  4. 2022Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentationcited by 63
  5. 2022Constrained Policy Optimization via Bayesian World Modelscited by 55
  6. 2023SafeDreamer: Safe Reinforcement Learning with World Modelscited by 50
  7. 2021Practical and Rigorous Uncertainty Bounds for Gaussian Process Regressioncited by 49
  8. 2022Investigating Compounding Prediction Errors in Learned Dynamics Modelscited by 47
  9. 2021Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challengescited by 40
  10. 2021Context-Aware Safe Reinforcement Learning for Non-Stationary Environmentscited by 33
  11. 2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 32
  12. 2021Model-based Constrained Reinforcement Learning using Generalized Control Barrier Functioncited by 30
38 more
  1. 2022Safe Reinforcement Learning for Legged Locomotioncited by 29
  2. 2022Sustainable Online Reinforcement Learning for Auto-biddingcited by 28
  3. 2021Stability Verification in Stochastic Control Systems via Neural Network Supermartingalescited by 24
  4. 2022Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guaranteescited by 24
  5. 2022Safe Reinforcement Learning Using Black-Box Reachability Analysiscited by 22
  6. 2024ActSafe: Active Exploration with Safety Constraints for Reinforcement Learningcited by 22
  7. 2022Learning Control Policies for Stochastic Systems with Reach-avoid Guaranteescited by 21
  8. 2024Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulationcited by 21
  9. 2021Safe Reinforcement Learning with Chance-constrained Model Predictive Controlcited by 18
  10. 2021Safe Continuous Control with Constrained Model-Based Policy Optimizationcited by 17
  11. 2022CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learningcited by 16
  12. 2023Robust Control for Dynamical Systems With Non-Gaussian Noise via Formal Abstractionscited by 16
  13. 2022Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interactioncited by 15
  14. 2024On Safety in Safe Bayesian Optimizationcited by 15
  15. 2021Robust Uncertainty Bounds in Reproducing Kernel Hilbert Spaces: A Convex Optimization Approachcited by 14
  16. 2021Model Error Propagation via Learned Contraction Metrics for Safe Feedback Motion Planning of Unknown Systemscited by 13
  17. 2021Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noisecited by 13
  18. 2022Online Weak-form Sparse Identification of Partial Differential Equationscited by 13
  19. 2023A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviorscited by 13
  20. 2025On Almost Surely Safe Alignment of Large Language Models at Inference-Timecited by 13
  21. 2021Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approachcited by 12
  22. 2023Compositional Policy Learning in Stochastic Control Systems with Formal Guaranteescited by 12
  23. 2024Safe Reinforcement Learning on the Constraint Manifold: Theory and Applicationscited by 12
  24. 2022Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learningcited by 11
  25. 2022Statistical Safety and Robustness Guarantees for Feedback Motion Planning of Unknown Underactuated Stochastic Systemscited by 11
  26. 2023Stable and Safe Reinforcement Learning via a Barrier-Lyapunov Actor-Critic Approachcited by 11
  27. 2024Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learningcited by 9
  28. 2023Can Learning Deteriorate Control? Analyzing Computational Delays in Gaussian Process-Based Event-Triggered Online Learningcited by 8
  29. 2021Uniform Error and Posterior Variance Bounds for Gaussian Process Regression with Application to Safe Controlcited by 7
  30. 2021MPC-based Reinforcement Learning for Economic Problems with Application to Battery Storagecited by 7
  31. 2021Adaptive Robust Model Predictive Control with Matched and Unmatched Uncertaintycited by 7
  32. 2021Improving Safety in Deep Reinforcement Learning using Unsupervised Action Planningcited by 7
  33. 2022VINet: Visual and Inertial-based Terrain Classification and Adaptive Navigation over Unknown Terraincited by 7
  34. 2025Safe LLM-Controlled Robots with Formal Guarantees via Reachability Analysiscited by 7
  35. 2022SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Criticscited by 6
  36. 2024Towards safe and tractable Gaussian process-based MPC: Efficient sampling within a sequential quadratic programming frameworkcited by 6
  37. 2026Safe Exploration via Policy Priorscited by 6
  38. 2021Provably Correct Training of Neural Network Controllers Using Reachability Analysiscited by 5

50 most cited of 116 All 116 (JSON)