Pages that link to "Item:Q1071658"
From MaRDI portal
The following pages link to Stationary policies and Markov policies in Borel dynamic programming (Q1071658):
Displayed 6 items.
- Finite-stage reward functions having the Markov adequacy property (Q1802324) (← links)
- The transformation method for continuous-time Markov decision processes (Q1937091) (← links)
- Markov-achievable payoffs for finite-horizon decision models. (Q1965904) (← links)
- MDPs with setwise continuous transition probabilities (Q2060367) (← links)
- On Generalized Bellman Equations and Temporal-Difference Learning (Q3305109) (← links)
- On Convergence of Value Iteration for a Class of Total Cost Markov Decision Processes (Q5502179) (← links)