Back to Results
First PageMeta Content



Dynamic Policy Programming with Function Approximation Mohammad Gheshlaghi Azar Radboud University Nijmegen Geert Grooteplein NoordEZ Nijmegen Netherlands
Add to Reading List

Document Date: 2011-03-17 08:53:29

Open Document

File Size: 194,25 KB

Share Result on Facebook

City

Denver / Belmont / Edmonton / Belmount / Fort Lauderdale / Pittsburgh / Vancouver / /

Company

Munos (2005) Lp / Neural Information Processing Systems / Cambridge University Press / MIT Press / Baxter / D. P. and Roy B. V. / /

Country

United States / Canada / United Kingdom / /

Currency

pence / /

/

Facility

University of Alberta / /

Holiday

Assumption / /

IndustryTerm

local search algorithm / policy-search method / gradient-based search / approximate algorithms / stable near-optimal solution / on-policy algorithms / double-loop algorithm / highdimensional systems / least-squares solution / regression algorithms / mountain car problem / sa best solution / relative entropy policy search / continuous systems / mountain-car problem / Natural actor-critic algorithms / policy search / mountain-car domain / approximate algorithm / learning algorithms / /

Organization

Cambridge University / MIT / University of Alberta / Department of Computing Science / /

Person

Mohammad Gheshlaghi Azar / Mansour / /

Position

D. J. / actor / critic / Natural actor-critic / natural actor critic / policy-gradient actor critic / /

ProgrammingLanguage

FL / L / J / /

ProvinceOrState

Alberta / British Columbia / Pennsylvania / Massachusetts / Colorado / /

PublishedMedium

Machine Learning / Journal of Artificial Intelligence Research / Journal of Machine Learning Research / /

Technology

local search algorithm / corresponding algorithm / DPP algorithm / REPS algorithm / approximate algorithms / API / approximate-DP algorithms / on-policy algorithms / ADPP algorithm / Machine Learning / Natural actor-critic algorithms / process control / double-loop algorithm / Reinforcement learning algorithms / artificial intelligence / AVI / single-loop / regression algorithms / final DPP algorithm / simulation / /

SocialTag