Back to Results
First PageMeta Content
Bayesian network / Thompson sampling / Reinforcement learning / Gibbs sampling / Prior probability / Hyperprior / Estimation theory / Supervised learning / Statistics / Bayesian statistics / Bayesian inference


Better Optimism By Bayes: Adaptive Planning with Rich Models Arthur Guez Gatsby Unit, UCL
Add to Reading List

Document Date: 2014-06-23 05:46:32

Open Document

File Size: 771,58 KB

Share Result on Facebook

City

Discussion Model / /

Company

Neural Information Processing Systems / Bayesian Networks / Monte Carlo / modeled using Bayesian Networks / /

Country

China / /

/

Facility

Wiley Online Library / Massachusetts Institute of Technology / University of Massachusetts Amherst / /

IndustryTerm

forward-search planning algorithm / online forward-search planning scheme / sample-based search / tree search / epoch-greedy algorithm / crude oil / contextual bandit algorithms / forward-search / search horizon / policy search / Online Library / natural gas / fine solution / oil exploration problem / search horizonRoss andand / Sample-based forwardsearch planning algorithms / search tree / search treeThus / oil / approximate solutions / on-line reward optimization / conventional algorithms / search efficiency / using sample-based search / /

Organization

Australian Mathematical Society / University of Massachusetts Amherst / Rich Models Arthur Guez Gatsby Unit / Peter Dayan Gatsby Unit / Massachusetts Institute of Technology / /

Person

Gill Spacing Cap Shape Stalk / Peter Dayan / Van Roy / David Silver / /

Position

myopic planner / associated Bayesian non-parametric model for it / rt / Bayes-Adaptive planner / /

ProvinceOrState

D / Massachusetts / /

PublishedMedium

Machine Learning / Journal of Artificial Intelligence Research / /

Technology

Alpha / BAMCP algorithm / thesupplementary BAMCP algorithm / artificial intelligence / forward-search planning algorithm / existing conventional algorithms / PSRL algorithm / GPS / forward-search / sample-based Bayes-adaptive planning algorithm / planning algorithm / Sample-based forwardsearch planning algorithms / contextual bandit algorithms / machine learning / existing planning algorithms / BOSS algorithm / simulation / epoch-greedy algorithm / α−UCB algorithm / /

URL

http /

SocialTag