Back to Results
First PageMeta Content
Convex optimization / Operations research / Linear programming / Gradient descent / Duality / Interior point method / Lagrangian relaxation / Reinforcement learning / Markov decision process / Mathematical optimization / Numerical analysis / Mathematical analysis


An Accelerated Gradient Method for Distributed Multi-Agent Planning with Factored MDPs Geoffrey J. Gordon Machine Learning Department Carnegie Mellon University
Add to Reading List

Document Date: 2011-11-28 10:53:32

Open Document

File Size: 201,58 KB

Share Result on Facebook

Company

Intel Corporation / /

/

Facility

Sue Ann Hong Computer Science Department Carnegie Mellon University / Factored MDPs Geoffrey J. Gordon Machine Learning Department Carnegie Mellon University / /

IndustryTerm

accelerated gradient algorithm / iterative shrinkage-thresholding algorithm / distributed algorithm / subgradient algorithm / distributed planning algorithm / relaxation algorithm / proximal gradient algorithm / optimum solution / /

Organization

Factored MDPs Geoffrey J. Gordon Machine Learning Department Carnegie Mellon University Pittsburgh / Sue Ann Hong Computer Science Department Carnegie Mellon University Pittsburgh / /

Person

Geoffrey J. Gordon / J. Andrew Bagnell / Anind K. Dey / Brian D. Ziebart / Ai / Amir Beck / Carlos Guestrin / Marc Teboulle / Sue Ann Hong / /

/

Position

left-forward / /

ProgrammingLanguage

V / L / /

ProvinceOrState

Pennsylvania / /

PublishedMedium

Machine Learning / /

Technology

accelerated gradient algorithm / gradient Lagrangian relaxation algorithm / distributed planning algorithm / subgradient algorithm / iterative shrinkage-thresholding algorithm / accelerated gradient Lagrangian relaxation algorithm / Machine Learning / Lagrangian relaxation algorithm / naturally distributed algorithm / overall Lagrangian relaxation algorithm / 2 3 Algorithm / proximal gradient algorithm / /

SocialTag