Pages that link to "Item:Q5529080"

The following pages link to Existence of a Stationary Control for a Markov Chain Maximizing the Average Reward (Q5529080):

Displaying 2 items.

• Continuous time control of Markov processes on an arbitrary state space: average return criterion (Q1223874) (← links)
• Policy iteration type algorithms for recurrent state Markov decision processes (Q1886500) (← links)