mlsanityData to 14 Oct 2026

Control invariant set enhanced safe reinforcement learning: improved sampling efficiency, guaranteed stability and robustness

arXiv 2305.15602 ↗First posted 24 May 2023eess.SY cs.AI cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning (RL) is an area of significant research interest, and safe RL in particular is attracting attention due to its ability to handle safety-driven constraints that are crucial for real-world applications. This work proposes a novel approach to RL training, called control invariant set (CIS) enhanced RL, which leverages the advantages of utilizing the explicit form of CIS to improve stability guarantees and sampling efficiency. Furthermore, the robustness of the proposed approach is investigated in the presence of uncertainty. The approach consists of two learning stages: offline and online. In the offline stage, CIS is incorporated into the reward design, initial state sampling, and state reset procedures. This incorporation of CIS facilitates improved sampling efficiency during the offline training process. In the online stage, RL is retrained whenever the predicted next step state is outside of the CIS, which serves as a stability criterion, by introducing a Safety Supervisor to examine the safety of the action and make necessary corrections. The stability analysis is conducted for both cases, with and without uncertainty. To evaluate the proposed approach, we apply it to a simulated chemical reactor. The results show a significant improvement in sampling efficiency during offline training and closed-loop stability guarantee in the online implementation, with and without uncertainty.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 17 of its 41 references that are in the map. First posted on arXiv 24 May 2023.

Builds on

17 of 41 references.

References · 17

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2017Safe Reinforcement Learning via Shieldingcited by 449
  3. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
  4. 2015Risk-Constrained Reinforcement Learning with Percentile Risk Criteriacited by 337
  5. 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 181
  6. 2021Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challengescited by 50
  7. 2019Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamicscited by 47
  8. 2020Safe Reinforcement Learning via Projection on a Safe Set: How to Achieve Optimality?cited by 34
  9. 2021Model-based Constrained Reinforcement Learning using Generalized Control Barrier Functioncited by 32
  10. 2021Computationally Efficient Safe Reinforcement Learning for Power Systemscited by 20
  11. 2019Practical Reinforcement Learning of Stabilizing Economic MPCcited by 17
  12. 2021Learning Region of Attraction for Nonlinear Systemscited by 16
5 more
  1. 2021Comparison between safety methods control barrier function vs. reachability analysiscited by 6
  2. 2016Computing Robust Controlled Invariant Sets of Linear Systemscited by 5
  3. 2021Robust economic model predictive control with zone trackingcited by 3
  4. 2020Computing robust control invariant sets of constrained nonlinear systems: A graph algorithm approachcited by 2
  5. 2023Control invariant set enhanced reinforcement learning for process control: improved sampling efficiency and guaranteed stabilitycited by 1

Built on by

Cited by year (2026 to 14 Oct)

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

2 papers.

  1. 2025Reinforcement Learning-based Control via Y-wise Affine Neural Networks (YANNs)cited by 2
  2. 2026Reinforcement Learning-based Control via Y-wise Affine Neural Networks: Comparative Case Studies for Chemical Processescited by 0