Stability-Certified Reinforcement Learning: A Control-Theoretic Perspective

Stability-Certified Reinforcement Learning: A Control-Theoretic Perspective

Blog Article

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 prostate-stimulator 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 Course a pied - Femme - Vetements - Cuissard 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.