mlsanityData to 14 Oct 2026

Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems

arXiv 2109.03861 ↗First posted 8 Sep 2021eess.SY cs.AI cs.ROcited by 16

Not on the map. Why?

Abstract (arXiv)

Neural network controllers have become popular in control tasks thanks to their flexibility and expressivity. Stability is a crucial property for safety-critical dynamical systems, while stabilization of partially observed systems, in many cases, requires controllers to retain and process long-term memories of the past. We consider the important class of recurrent neural networks (RNN) as dynamic controllers for nonlinear uncertain partially-observed systems, and derive convex stability conditions based on integral quadratic constraints, S-lemma and sequential convexification. To ensure stability during the learning and control process, we propose a projected policy gradient method that iteratively enforces the stability conditions in the reparametrized space taking advantage of mild additional information on system dynamics. Numerical experiments show that our method learns stabilizing controllers while using fewer samples and achieving higher final performance compared with policy gradient.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 28 of its 65 references that are in the map. First posted on arXiv 8 Sep 2021.

Builds on

28 of 65 references.

References · 28

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Continuous control with deep reinforcement learningcited by 3,407
  3. 2015End-to-End Training of Deep Visuomotor Policiescited by 875
  4. 2016CVXPY: A Python-Embedded Modeling Language for Convex Optimizationcited by 641
  5. 2019Deep Equilibrium Modelscited by 615
  6. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 366
  7. 2016Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collectioncited by 316
  8. 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 297
  9. 2018Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulatorcited by 250
  10. 2018A Tour of Reinforcement Learning: The View from Continuous Controlcited by 151
  11. 2019Implicit Deep Learningcited by 124
  12. 2014Analysis and Design of Optimization Algorithms via Integral Quadratic Constraintscited by 105
16 more
  1. 2019Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programmingcited by 101
  2. 2015Memory-based control with recurrent neural networkscited by 78
  3. 2020Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functionscited by 68
  4. 2019Policy Optimization for H2 Linear Control with H_∞ Robustness Guarantee: Implicit Regularization and Global Convergencecited by 46
  5. 2020Stability Analysis using Quadratic Constraints for Systems with Neural Network Controllerscited by 44
  6. 2020Enforcing robust control guarantees within neural network policiescited by 40
  7. 2020Imitation Learning with Stability and Safety Guaranteescited by 34
  8. 2018Stability-certified reinforcement learning: A control-theoretic perspectivecited by 31
  9. 2021Analysis of the Optimization Landscape of Linear Quadratic Gaussian (LQG) Controlcited by 28
  10. 2019Exploring applications of deep reinforcement learning for real-world autonomous driving systemscited by 18
  11. 2019From self-tuning regulators to reinforcement learning and back againcited by 17
  12. 2017Convex Parameterizations and Fidelity Bounds for Nonlinear Identification and Reduced-Order Modellingcited by 8
  13. 2019H_∞ Model-free Reinforcement Learning with Robust Stability Guaranteecited by 7
  14. 2021Linear systems with neural network nonlinearities: Improved stability analysis via acausal Zames-Falb multiplierscited by 6
  15. 2017Exponential Stability Analysis via Integral Quadratic Constraintscited by 1
  16. 2021Model predictive control for linear uncertain systems using integral quadratic constraintscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 3; 2023: 2; 2024: 6; 2025: 2; 2026: 1.

16 papers.

Sort:

By area:

  1. 2021Learning over All Stabilizing Nonlinear Controllers for a Partially-Observed Linear Systemcited by 14
  2. 2022Neural System Level Synthesis: Learning over All Stabilizing Policies for Nonlinear Systemscited by 11
  3. 2024A Review of Safe Reinforcement Learning Methods for Modern Power Systemscited by 11
  4. 2021Youla-REN: Learning Nonlinear Feedback Policies with Robust Stability Guaranteescited by 10
  5. 2024Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulationcited by 9
  6. 2022Synthesis of Stabilizing Recurrent Equilibrium Network Controllerscited by 8
  7. 2024Learning to Boost the Performance of Stable Nonlinear Systemscited by 7
  8. 2024Synthesizing Neural Network Controllers with Closed-Loop Dissipativity Guaranteescited by 4
  9. 2024Ensuring Both Positivity and Stability Using Sector-Bounded Nonlinearity for Systems with Neural Network Controllerscited by 4
  10. 2023Stabilizing reinforcement learning control: A modular framework for optimizing over all stable behaviorcited by 3
  11. 2024Preparing for Black Swans: The Antifragility Imperative for Machine Learningcited by 1
  12. 2022Robust Recurrent Neural Network to Identify Ship Motion in Open Water with Performance Guarantees -- Technical Reportcited by 0
4 more
  1. 2023Rational Neural Network Controllerscited by 0
  2. 2025Stabilization of industrial processes with time series machine learningcited by 0
  3. 2025MSACL: Multi-Step Actor-Critic Learning with Lyapunov Certificates for Exponentially Stabilizing Controlcited by 0
  4. 2026Learning Provable Neural Network Observer for Uncertain Dynamical Systemscited by 0