Skip navigation
Skip navigation

Policy Gradient Methods: Variance Reduction and Stochastic Convergence

Greensmith, Evan

Description

In a reinforcement learning task an agent must learn a policy for performing actions so as to perform well in a given environment. Policy gradient methods consider a parameterized class of policies, and using a policy from the class, and a trajectory through the environment taken by the agent using this policy, estimate the performance of the policy with respect to the parameters. Policy gradient methods avoid some of the problems of value function methods, such as policy degradation,...[Show more]

dc.contributor.authorGreensmith, Evan
dc.date.accessioned2008-06-16T06:35:31Z
dc.date.accessioned2011-01-04T02:38:37Z
dc.date.available2008-06-16T06:35:31Z
dc.date.available2011-01-04T02:38:37Z
dc.identifier.otherb2247206x
dc.identifier.urihttp://hdl.handle.net/1885/47105
dc.description.abstractIn a reinforcement learning task an agent must learn a policy for performing actions so as to perform well in a given environment. Policy gradient methods consider a parameterized class of policies, and using a policy from the class, and a trajectory through the environment taken by the agent using this policy, estimate the performance of the policy with respect to the parameters. Policy gradient methods avoid some of the problems of value function methods, such as policy degradation, where inaccuracy in the value function leads to the choice of a poor policy. However, the estimates produced by policy gradient methods can have high variance. ¶ ...
dc.language.isoen
dc.rights.uriThe Australian National University
dc.subjectreinforcement learning
dc.subjectpolicy gradient
dc.subjectstochastic convergence
dc.subjectvariance reduction
dc.titlePolicy Gradient Methods: Variance Reduction and Stochastic Convergence
dc.typeThesis (PhD)
dcterms.valid2005
local.description.refereedyes
local.type.degreeDoctor of Philosophy (PhD)
dc.date.issued2005
local.contributor.affiliationResearch School of Information Sciences and Engineering, Computer Sciences Laboratory
local.contributor.affiliationThe Australian National University
local.identifier.doi10.25911/5d7a2a01dcebe
local.mintdoimint
CollectionsOpen Access Theses

Download

File Description SizeFormat Image
02whole.pdf1.19 MBAdobe PDFThumbnail
01front.pdf69.02 kBAdobe PDFThumbnail


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator