quotation:		[Copy]
		Xiren Cao,Junyu Zhang.[en_title][J].Control Theory and Technology,2004,2(1):65~68.[Copy]

This Paper:Browse 695 Download 94	码上扫一扫！

XirenCao,JunyuZhang
0 Fontlarge +\|Default\|Small
()

摘要:

关键词:

DOI：

Received:January 13, 2004

基金项目:

Performance sensitivities for parameterized Markov systems

Xiren Cao,Junyu Zhang

(Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong)

Abstract:

It is known that the performance potentials (or equivalentiy, perturbation realization factors) can be used as building blocks for performance sensitivities of Markov systems. In parameterized systems, the changes in parameters may only affect some states, and the explicit transition probability matrix may not be known. In this paper, we use an example to show that we can use potentials to construct performance sensitivities in a more flexible way; only the potentials at the affected states need to be estimated, and the transition probability matrix need not be known. Policy iteration algorithms, which are simpler than the standard one, can be established.

Key words: Perturbation analysis Markov decision processes Policy iteration Reinforcement learning Perturbation realization