Back to Results
First PageMeta Content
Decision theory / Markov models / Mathematical optimization / Dynamic programming / Reinforcement learning / Markov decision process / Markov chain / Value of information / Variance / Statistics / Probability and statistics / Markov processes


Selecting Computations: Theory and Applications Nicholas Hay and Stuart Russell Computer Science Division University of California Berkeley, CA 94720
Add to Reading List

Document Date: 2012-10-04 09:08:48


Open Document

File Size: 324,93 KB

Share Result on Facebook

City

Minneapolis / /

Company

AUAI Press / MIT Press / Computer Sciences / Bernstein / AAAI Press / John Wiley & Sons Inc. / John Wiley & Sons / /

/

Facility

Stuart Russell Computer Science Division University of California Berkeley / Carnegie-Mellon University / University of California / Computer Science Ben-Gurion University / /

IndustryTerm

tree search / game tree search / search states / tree search algorithms / combinatorial search problems / Classical algorithms / search rollouts / search tree depth / search budget / above approximate algorithms / earlier search states / typical game-playing algorithm / search domain / search state / bandit algorithms / approximate solution / heuristic algorithms / bandit algorithm / flat sampling algorithms / game-playing search / computing / gametree search / approximate solutions / /

Organization

University of California / National Science Foundation / American Statistical Association / Israel Science Foundation / Stuart Russell Computer Science Division University / MIT / Royal Statistical Society / Machine Intelligence / Paul Ivanier Center for Robotics Research and Production Management / Tolpin and Solomon Eyal Shimony Department / Computer Science Ben-Gurion University of the Negev Beer Sheva / Carnegie-Mellon University / Pittsburgh / William Frankel Center for Computer Sciences / /

Person

Monte-Carlo Go / Oliver / Hall London / Solomon Eyal Shimony / Stuart Russell / Boyd / Chapman London / Nicholas Hay / /

Position

Bernoulli metalevel probability model / each arm / General / Dean / strong player / /

ProvinceOrState

Pennsylvania / California / /

PublishedMedium

Journal of the Royal Statistical Society / Machine Learning / Journal of the American Statistical Association / /

Technology

typical game-playing algorithm / above approximate algorithms / MoGo algorithm / UCB1 bandit algorithm / UCT algorithm / Monte-Carlo tree search algorithms / Machine Learning / bandit algorithms / artificial intelligence / using bandit algorithms / flat sampling algorithms / simulation / /

SocialTag