The following pages link to (Q4331900):
Displaying 4 items.
- A note on the convergence rate of the value iteration scheme in controlled Markov chains (Q1128695) (← links)
- The value functions of Markov decision processes (Q1755814) (← links)
- Continuity of Optimal Values and Solutions for Control of Markov Chains with Constraints (Q4507404) (← links)
- ON THE EXISTENCE OF THE PUISEUX EXPANSION OF THE DISCOUNTED REWARDS: A COUNTEREXAMPLE (Q4955534) (← links)