Stability-certified reinforcement learning: A control-theoretic perspective

2018-10-26 · Ming Jin, Javad Lavaei

We investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems. We show that by regulating the input-output gradients of policies, strong guarantees of robust stability can be obtained based on a proposed semidefinite programming feasibility problem. The method is able to certify a large set of stabilizing controllers by exploiting problem-specific structures; furthermore, we analyze and establish its (non)conservatism. Empirical evaluations on two decentralized control tasks, namely multi-flight formation and power system frequency regulation, demonstrate that the reinforcement learning agents can have high performance within the stability-certified parameter space, and also exhibit stable learning behaviors in the long run.

📄 PDF Abstract BibTeX arXiv:1810.11505

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Stability-Certified Reinforcement Learning via Spectral Normalization

2020-12-26 · Ryoichi Takase, Nobuyuki Yoshikawa, Toshisada Mariyama, Takeshi Tsuchiya

In this article, two types of methods from different perspectives based on spectral normalization are described for ensuring the stability of the system controlled by a neural network. The first one is that the L2 gain o…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Safe and Optimal Variable Impedance Control via Certified Reinforcement Learning

2025-11-20 · Shreyas Kumar, Ravi Prakash arxiv

Reinforcement learning (RL) offers a powerful approach for robots to learn complex, collaborative skills by combining Dynamic Movement Primitives (DMPs) for motion and Variable Impedance Control (VIC) for compliant inter…

Reinforcement Learning

Joint Differentiable Optimization and Verification for Certified Reinforcement Learning

2022-01-28 · YiXuan Wang, Simon Zhan, Zhilu Wang, Chao Huang 외

In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties (e.g., safety, stability) under the learned controller. However, as existing methods typica…

Bilevel Optimization Model-based Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Stable Inverse Reinforcement Learning: Policies from Control Lyapunov Landscapes

2024-05-14 · Samuel Tesfazgi, Leonhard Sprandl, Armin Lederer, Sandra Hirche

Learning from expert demonstrations to flexibly program an autonomous system with complex behaviors or to predict an agent's behavior is a powerful tool, especially in collaborative control settings. A common method to s…

reinforcement-learning Reinforcement Learning

Actor-Critic Reinforcement Learning for Control with Stability Guarantee

2020-04-29 · Minghao Han, Lixian Zhang, Jun Wang, Wei Pan

Reinforcement Learning (RL) and its integration with deep learning have achieved impressive performance in various robotic control tasks, ranging from motion planning and navigation to end-to-end visual manipulation. How…

Motion Planning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)