Next:
Finite Horizon
Finite Horizon
Markovian Policy
Summary
An Algorithm for Constructing an Optimal Policy
Computational Complexity
Example: The Recruiting Problem
The Problem
The Goal
The Solution
Optimality Proof
A Numeric Example
An Asymptotic Example
Conclusion
Infinite Horizon Problems
The Return Function
Example 1
The Expected Discounted Sum Return Function
Markovian Policy
The Return Function
About this document ...
Yishay Mansour
1999-11-18
