Title :
A Matrosov Theorem for Adversarial Markov Decision Processes
Author_Institution :
Electr. & Comput. Eng. Dept., Univ. of California, Santa Barbara, Santa Barbara, CA, USA
Abstract :
Matrosov´s relaxation of Lyapunov conditions for uniform global asymptotic stability in time-varying systems is extended to stochastic, set-valued discrete-time systems. Nested Matrosov functions are used to give conditions for stability that complement invariance principles for time-invariant systems. Unlike invariance principles, Matrosov functions also can be applied to general time-varying systems.
Keywords :
Lyapunov methods; Markov processes; asymptotic stability; differential equations; stochastic systems; time-varying systems; Lyapunov conditions; Matrosov theorem; adversarial Markov decision processes; differential equations; discrete-time systems; global asymptotic stability; nested Matrosov functions; stochastic systems; time-varying systems; Asymptotic stability; Computers; Decentralized control; Linear systems; Lyapunov methods; Markov processes; Time-varying systems;
Journal_Title :
Automatic Control, IEEE Transactions on
DOI :
10.1109/TAC.2013.2250073
