Furmston, T;
Barber, D;
(2012)
A Unifying Perspective of Parametric Policy Search Methods for Markov Decision Processes.
In:
Advances in Neural Information Processing Systems 25 (NIPS 2012).
(pp. 2726 - 2734).
Neural Information Processing Systems Foundation
Preview |
Text
Barber_NIPS2012_1261%5B1%5D.pdf Download (1MB) | Preview |
Abstract
Parametric policy search algorithms are one of the methods of choice for the optimisation of Markov Decision Processes, with Expectation Maximisation and natural gradient ascent being considered the current state of the art in the field. In this article we provide a unifying perspective of these two algorithms by showing that their step-directions in the parameter space are closely related to the search direction of an approximate Newton method. This analysis leads naturally to the consideration of this approximate Newton method as an alternative gradient-based method for Markov Decision Processes. We are able show that the algorithm has numerous desirable properties, absent in the naive application of Newton's method, that make it a viable alternative to either Expectation Maximisation or natural gradient ascent. Empirical results suggest that the algorithm has excellent convergence and robustness properties, performing strongly in comparison to both Expectation Maximisation and natural gradient ascent.
Type: | Proceedings paper |
---|---|
Title: | A Unifying Perspective of Parametric Policy Search Methods for Markov Decision Processes |
Event: | Neural Information Processing Systems 2012 |
Open access status: | An open access version is available from UCL Discovery |
Publisher version: | http://papers.nips.cc/paper/4576-a-unifying-perspe... |
Language: | English |
Additional information: | Copyright © The Authors 2012. |
UCL classification: | UCL UCL > Provost and Vice Provost Offices UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
URI: | https://discovery.ucl.ac.uk/id/eprint/1388934 |
Archive Staff Only
View Item |