Back to Results
First PageMeta Content
Systems theory / Mathematical optimization / Equations / Operations research / Stochastic control / Markov decision process / Lookahead / Bellman equation / Automated planning and scheduling / Statistics / Dynamic programming / Control theory


LRTDP vs. UCT for Online Probabilistic Planning Andrey Kolobov Mausam Daniel S. Weld
Add to Reading List

Document Date: 2013-08-13 03:53:42

Open Document

File Size: 258,87 KB

Share Result on Facebook

City

Aberdeen / O. / Value Iteration / /

Company

Princeton University Press / Amazon / P ROST / Bellman / Tioga Publishing / John Wiley & Sons / /

Country

United States / /

/

Facility

Engineering University of Washington Seattle / University of Freiburg / /

IndustryTerm

online / tree search / adaptable planning algorithm / online version / assignment operator / online manner / probabilistic planning algorithm / online use / competition server / online mode / online setting / heuristic search algorithm / online versions / basic algorithm / inefficient offline planning algorithm / Online Probabilistic Planning Andrey Kolobov Mausam Daniel S. Weld / /

Organization

Computer Science and Engineering University of Washington Seattle / National Science Foundation / Princeton University / MDP V / University of Freiburg / /

Person

Thomas Keller / P ROST / G LUTTON / Patrick Eyerich / Daniel S. Weld / Andrey Kolobov Mausam Daniel / /

Position

UCT-based planner / online planner / planner / factored policy gradient planner / engineer / /

Technology

RAM / heuristic search algorithm / MDP algorithms / relatively inefficient offline planning algorithm / artificial intelligence / UCT algorithm / adaptable planning algorithm / probabilistic planning algorithm / MDP solution algorithms / two algorithms / basic algorithm / /

URL

http /

SocialTag