Back to Results
First PageMeta Content
Systems theory / Dynamic programming / Equations / Operations research / Stochastic control / Lipschitz continuity / Optimal control / S0 / Markov decision process / Statistics / Mathematical optimization / Control theory


Sample Complexity and Performance Bounds for Non-parametric Approximate Linear Programming Jason Pazis and Ronald Parr Department of Computer Science, Duke University Durham, NC 27708 {jpazis,parr}@cs.duke.edu
Add to Reading List

Document Date: 2013-04-10 17:56:12


Open Document

File Size: 291,37 KB

Share Result on Facebook

City

Kernel / Haifa / New York / /

Company

Lr Lp / Neural Information Processing Systems / AAAI Press / /

Country

Israel / United States / /

/

Facility

Duke University / /

IndustryTerm

nonlinear systems / non-parametric algorithms / approximate solution / /

Organization

Ronald Parr Department of Computer Science / Association for the Advancement / National Science Foundation / Duke University Durham / /

Person

Taylor / Jason Pazis / Vincent Conitzer / Ronald Parr / Mauro Maggioni / /

Position

representative / /

ProgrammingLanguage

ML / /

PublishedMedium

Journal of Machine Learning Research / Machine Learning / /

Technology

Machine Learning / batch mode RL algorithms / artificial intelligence / non-parametric algorithms / ALP algorithm / NP-ALP algorithm / /

URL

www.aaai.org / /

SocialTag