Dynamic programming through the lens of semismooth Newton-type methods
Policy iteration and value iteration are at the core of many (approximate) dynamic
programming methods. For Markov Decision Processes with finite state and action spaces …
programming methods. For Markov Decision Processes with finite state and action spaces …
Dynamic programming through the lens of semismooth Newton-type methods (extended version)
Policy iteration and value iteration are at the core of many (approximate) dynamic
programming methods. For Markov Decision Processes with finite state and action spaces …
programming methods. For Markov Decision Processes with finite state and action spaces …
Inexact GMRES policy iteration for large-scale Markov decision processes
Policy iteration enjoys a local quadratic rate of contraction, but its iterations are
computationally expensive for Markov decision processes (MDPs) with a large number of …
computationally expensive for Markov decision processes (MDPs) with a large number of …