Search Results for author: Thomas Furmston

Found 2 papers, 0 papers with code

A Gauss-Newton Method for Markov Decision Processes

no code implementations29 Jul 2015 Thomas Furmston, Guy Lever

In this work we investigate approximate Newton methods for policy optimization in Markov Decision Processes (MDPs).

Affine Transformation

A Unifying Perspective of Parametric Policy Search Methods for Markov Decision Processes

no code implementations NeurIPS 2012 Thomas Furmston, David Barber

This analysis leads naturally to the consideration of this approximate Newton method as an alternative gradient-based method for Markov Decision Processes.

Cannot find the paper you are looking for? You can Submit a new open access paper.