This article provides an introductory tutorial on structural results in partially observed Markov decision processes (POMDPs). Typically, computing the optimal policy of a POMDP is computationally intractable. We use lattice program- ming methods to characterize the structure of the optimal policy of a POMDP without brute force computations.
Myopic Bounds for Optimal Policy of POMDPs: An extension of Lovejoy's structural results
A distance for probability spaces, and long-term values in Markov Decision Processes and Repeated Games
Convergence Analysis of the Approximate Newton Method for Markov Decision Processes
![QR code for arXiv:1512.03873 [math.OC]](http://oss.arxitics.com/images/favicon.svg)