.png){kind=icon}
.png){kind=icon}
Return
Stability-Certified Reinforcement Learning: A Control-Theoretic Perspective
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2020.3045114.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems. We show that by regulating the partial 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.
Keywords:
Reinforcement learning
Power system stability
Stability criteria
Safety
Decentralized control
Numerical stability
Control theory
Reinforcement learning
robust control
decentralized control synthesis
safe reinforcement learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
