Bayesian Policy Gradient Algorithms
Full Text: nips06.pdfPolicy gradient methods are reinforcement learning algorithms that adapt a parameterized policy by following a performance gradient estimate. Conventional policy gradient methods use Monte-Carlo techniques to estimate this gradient. Since Monte Carlo methods tend to have high variance, a large number of samples is required, resulting in slow convergence. In this paper, we propose a Bayesian framework that models the policy gradient as a Gaussian process. This reduces the number of samples needed to obtain accurate gradient estimates. Moreover, estimates of the natural gradient as well as a measure of the uncertainty in the gradient estimates are provided at little extra cost.
Citation
M. Ghavamzadeh, Y. Engel. "Bayesian Policy Gradient Algorithms". Neural Information Processing Systems (NIPS), December 2006.Keywords: | machine learning |
Category: | In Conference |
BibTeX
@incollection{Ghavamzadeh+Engel:NIPS06, author = {Mohammad Ghavamzadeh and Yaakov Engel}, title = {Bayesian Policy Gradient Algorithms}, booktitle = {Neural Information Processing Systems (NIPS)}, year = 2006, }Last Updated: February 01, 2008
Submitted by Nelson Loyola