mlsanityData to 7 Oct 2026

Reinforcement Learning with Ensemble Model Predictive Safety Certification

arXiv 2402.04182 ↗First posted 6 Feb 2024cs.LG cs.ROcited by 4

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning algorithms need exploration to learn. However, unsupervised exploration prevents the deployment of such algorithms on safety-critical tasks and limits real-world deployment. In this paper, we propose a new algorithm called Ensemble Model Predictive Safety Certification that combines model-based deep reinforcement learning with tube-based model predictive control to correct the actions taken by a learning agent, keeping safety constraint violations at a minimum through planning. Our approach aims to reduce the amount of prior knowledge about the actual system by requiring only offline data generated by a safe controller. Our results show that we can achieve significantly fewer constraint violations than comparable reinforcement learning methods.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 21 of its 36 references that are in the map. First posted on arXiv 6 Feb 2024.

Builds on

21 of 36 references.

References · 21

  1. 2016Concrete Problems in AI Safetycited by 1,582
  2. 2017Constrained Policy Optimizationcited by 928
  3. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 753
  4. 2018Reward Constrained Policy Optimizationcited by 397
  5. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 347
  6. 2019Control Barrier Functions: Theory and Applicationscited by 332
  7. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 288
  8. 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 256
  9. 2018Safe Exploration in Continuous Action Spacescited by 237
  10. 2020Recovery RL: Safe Reinforcement Learning with Learned Recovery Zonescited by 156
  11. 2019Lyapunov-based Safe Policy Optimization for Continuous Controlcited by 140
  12. 2020Learning to be Safe: Deep RL with a Safety Criticcited by 109
9 more
  1. 2017AI Safety Gridworldscited by 108
  2. 2018A predictive safety filter for learning-based control of constrained nonlinear dynamical systemscited by 91
  3. 2020Learning Control Barrier Functions from Expert Demonstrationscited by 88
  4. 2018Safe Reinforcement Learning with Model Uncertainty Estimatescited by 70
  5. 2018Accelerated Primal-Dual Policy Optimization for Safe Reinforcement Learningcited by 61
  6. 2021Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violationscited by 36
  7. 2018Linear model predictive safety certification for learning-based controlcited by 34
  8. 2019Probabilistic model predictive safety certification for learning-based controlcited by 20
  9. 2021Lyapunov Barrier Policy Optimizationcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forwardcited by 5
  2. 2025HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agentscited by 4
  3. 2026Uncertainty-Aware Predictive Safety Filters for Probabilistic Neural Network Dynamicscited by 1
  4. 2026All Models are Wrong, Knowing Where is Useful: On Model Uncertainty in Reinforcement Learningcited by 0