scientific article; zbMATH DE number 176107

From MaRDI portal
Publication:4035208





[For the entire collection see Zbl 0752.00048.] For usual average reward Markov decision problems (MDPs) with a constraint based on a second reward structure of the same type there exist optimal stationary policies which are randomized for only one state. The same result is shown here for maximizing the growth rate in multiplicative MDPs, using monotonicity of the growth rate in the randomizing parameter (instead of linearity which holds in the additive case).











This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4035208)