mlsanityData to 14 Oct 2026

Probabilistically safe and efficient model-based reinforcement learning

arXiv 2504.00626 ↗First posted 1 Apr 2025eess.SY cs.SYcited by 3

On the map: Deep reinforcement learning methods → Safe and constrained RL

Abstract (arXiv)

This paper proposes tackling safety-critical stochastic Reinforcement Learning (RL) tasks with a sample-based, model-based approach. At the core of the method lies a Model Predictive Control (MPC) scheme that acts as function approximation, providing a model-based predictive control policy. To ensure safety, a probabilistic Control Barrier Function (CBF) is integrated into the MPC controller. To approximate the effects of stochasticies in the optimal control formulation and to fulfil the probabilistic CBF condition, a sample-based approach with guarantees is employed. Furthermore, to counterbalance the additional computational burden due to sampling, a learnable terminal cost formulation is included in the MPC objective. An RL algorithm is deployed to learn both the terminal cost and the CBF constraint. Results from a numerical experiment on a constrained LTI problem corroborate the effectiveness of the proposed methodology in reducing computation time while preserving control performance and safety.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods. Builds on 14 of its 35 references that are in the map. First posted on arXiv 1 Apr 2025.

Builds on

14 of 35 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Reinforcement Learning-based Receding Horizon Control using Adaptive Control Barrier Functions for Safety-Critical Systems26 Mar

Other references · 13

  1. 2017A Brief Survey of Deep Reinforcement Learningcited by 483
  2. 2019Control Barrier Functions: Theory and Applicationscited by 372
  3. 2019Safe Reinforcement Learning Using Robust MPCcited by 85
  4. 2019Data-driven Economic NMPC using Reinforcement Learningcited by 68
  5. 2020Safety-Critical Model Predictive Control with Discrete-Time Control Barrier Functioncited by 49
  6. 2025Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classificationcited by 26
  7. 2013The Scenario Approach for Stochastic Model Predictive Control with Bounds on Closed-Loop Constraint Violationscited by 24
  8. 2020Practical Reinforcement Learning For MPC: Learning from sparse objectives in under an hour on a real robotcited by 17
  9. 2019Computing Probabilistic Controlled Invariant Setscited by 6
  10. 2022Learning safety in model-based Reinforcement Learning using MPC and Gaussian Processescited by 4
  11. 2024Probabilistically safe controllers based on control barrier functions and scenario model predictive controlcited by 3
  12. 2022Approximate Dynamic Programming for Constrained Linear Systems: A Piecewise Quadratic Approximation Approachcited by 2
1 more
  1. 2023Parameterized Barrier Functions to Guarantee Safety under Uncertaintycited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Safety-Critical Reinforcement Learning with Viability-Based Action Shielding for Hypersonic Longitudinal Flightcited by 0
  2. 2026A Control Barrier Function-Constrained Model Predictive Control Framework for Safe Reinforcement Learningcited by 0
  3. 2026Learning-Based Stochastic Optimal Control with Infinite-Horizon Probabilistic Constraintscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Safe model-based Reinforcement Learning via Model Predictive Control and Control Barrier Functions
  2. 2025A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functions
  3. 2026CAPSULE: Control-Theoretic Action Perturbations for Safe Uncertainty-Aware Reinforcement Learning
  4. 2024Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems
  5. 2024Safe Deep Model-Based Reinforcement Learning with Lyapunov Functions
  6. 2025Safety Reinforced Model Predictive Control (SRMPC): Improving MPC with Reinforcement Learning for Motion Planning in Autonomous Driving
  7. 2026Sampling-Based Safe Reinforcement Learning
  8. 2025Probabilistic Shielding for Safe Reinforcement Learning