Lyapunov Stability Learning with Nonlinear Control via Inductive Biases

• URL: http://arxiv.org/abs/2511.01283v1
• Date: Mon, 03 Nov 2025 06:57:37 GMT
• Title: Lyapunov Stability Learning with Nonlinear Control via Inductive Biases
• Authors: Yupu Lu, Shijie Lin, Hao Xu, Zeqing Zhang, Jia Pan,
• Abstract summary: Finding a control Lyapunov function (CLF) in a dynamical system with a controller is an effective way to guarantee stability.<n>Recent deep learning models representing CLFs have been applied into a learner-verifier framework to identify satisfiable candidates.<n>We improve this framework by treating Lyapunov conditions as inductive biases and design a neural CLF and a CLF-based controller guided by this knowledge.
• Score: 21.083462885546556
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Finding a control Lyapunov function (CLF) in a dynamical system with a controller is an effective way to guarantee stability, which is a crucial issue in safety-concerned applications. Recently, deep learning models representing CLFs have been applied into a learner-verifier framework to identify satisfiable candidates. However, the learner treats Lyapunov conditions as complex constraints for optimisation, which is hard to achieve global convergence. It is also too complicated to implement these Lyapunov conditions for verification. To improve this framework, we treat Lyapunov conditions as inductive biases and design a neural CLF and a CLF-based controller guided by this knowledge. This design enables a stable optimisation process with limited constraints, and allows end-to-end learning of both the CLF and the controller. Our approach achieves a higher convergence rate and larger region of attraction (ROA) in learning the CLF compared to existing methods among abundant experiment cases. We also thoroughly reveal why the success rate decreases with previous methods during learning.

Related papers

• CRL-VLA: Continual Vision-Language-Action Learning [40.18167835795084]
  Continual Reinforcement Learning is a promising pathway for deploying VLA models in lifelong robotic scenarios.<n>We introduce CRL-VLA, a framework for continual post-training of VLA models with rigorous theoretical bounds.<n>We derive a unified performance bound linking the stability-plasticity trade-off to goal-conditioned advantage magnitude, scaled by policy divergence.
  arXiv  Detail & Related papers  (2026-02-03T12:09:53Z)
• Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning [77.92320830700797]
  Reinforcement Learning has played a central role in enabling reasoning capabilities of Large Language Models.<n>We propose a tractable computational framework that tracks and leverages curvature information during policy updates.<n>The algorithm, Curvature-Aware Policy Optimization (CAPO), identifies samples that contribute to unstable updates and masks them out.
  arXiv  Detail & Related papers  (2025-10-01T12:29:32Z)
• Certifying Stability of Reinforcement Learning Policies using Generalized Lyapunov Functions [15.306107403623075]
  We study the problem of certifying the stability of closed-loop systems under control policies derived from optimal control or reinforcement learning (RL)<n>Classical Lyapunov methods require a strict step-wise decrease in the Lyapunov function but such a certificate is difficult to construct for a learned control policy.<n>We formulate an approach to learn generalized Lyapunov functions by augmenting RL value functions with neural network residual terms.
  arXiv  Detail & Related papers  (2025-05-16T07:36:40Z)
• Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation [67.63756749551924]
  Learning-based neural network (NN) control policies have shown impressive empirical performance in a wide range of tasks in robotics and control. Lyapunov stability guarantees over the region-of-attraction (ROA) for NN controllers with nonlinear dynamical systems are challenging to obtain. We demonstrate a new framework for learning NN controllers together with Lyapunov certificates using fast empirical falsification and strategic regularizations.
  arXiv  Detail & Related papers  (2024-04-11T17:49:15Z)
• Learning Stability Attention in Vision-based End-to-end Driving Policies [100.57791628642624]
  We propose to leverage control Lyapunov functions (CLFs) to equip end-to-end vision-based policies with stability properties. We present an uncertainty propagation technique that is tightly integrated into att-CLFs.
  arXiv  Detail & Related papers  (2023-04-05T20:31:10Z)
• Joint Differentiable Optimization and Verification for Certified Reinforcement Learning [91.93635157885055]
  In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties. We propose a framework that jointly conducts reinforcement learning and formal verification.
  arXiv  Detail & Related papers  (2022-01-28T16:53:56Z)
• Closing the Closed-Loop Distribution Shift in Safe Imitation Learning [80.05727171757454]
  We treat safe optimization-based control strategies as experts in an imitation learning problem. We train a learned policy that can be cheaply evaluated at run-time and that provably satisfies the same safety guarantees as the expert.
  arXiv  Detail & Related papers  (2021-02-18T05:11:41Z)
• Constrained Model-Free Reinforcement Learning for Process Optimization [0.0]
  Reinforcement learning (RL) is a control approach that can handle nonlinear optimal control problems. Despite the promise exhibited, RL has yet to see marked translation to industrial practice. We propose an 'oracle'-assisted constrained Q-learning algorithm that guarantees the satisfaction of joint chance constraints with a high probability.
  arXiv  Detail & Related papers  (2020-11-16T13:16:22Z)
• Gaussian Process-based Min-norm Stabilizing Controller for Control-Affine Systems with Uncertain Input Effects and Dynamics [90.81186513537777]
  We propose a novel compound kernel that captures the control-affine nature of the problem. We show that this resulting optimization problem is convex, and we call it Gaussian Process-based Control Lyapunov Function Second-Order Cone Program (GP-CLF-SOCP)
  arXiv  Detail & Related papers  (2020-11-14T01:27:32Z)
• Neural Lyapunov Control [14.534839557929375]
  We propose new methods for learning control policies and neural network Lyapunov functions for nonlinear control problems. The framework consists of a learner that attempts to find the control and Lyapunov functions, and a falsifier that finds counterexamples to quickly guide the learner towards solutions.
  arXiv  Detail & Related papers  (2020-05-01T21:18:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.