Pages that link to "Item:Q1785275"

The following pages link to Modified policy iteration algorithms are not strongly polynomial for discounted dynamic programming (Q1785275):

Displaying 3 items.

• Improved bound on the worst case complexity of policy iteration (Q1785761) (← links)
• Complexity bounds for approximately solving discounted MDPs by value iterations (Q2661516) (← links)
• On the reduction of total‐cost and average‐cost MDPs to discounted MDPs (Q3120606) (← links)