Back to Results
First PageMeta Content
Dynamic programming / Stochastic control / Markov models / Statistical mechanics / Partially observable Markov decision process / Monte Carlo method / Reinforcement learning / Markov decision process / Automated planning and scheduling / Statistics / Probability and statistics / Markov processes


Document Date: 2013-01-31 06:44:50


Open Document

Share Result on Facebook

City

Sydney / /

Company

Neural Information Processing Systems / MIT Press / /

Country

Australia / /

/

Event

Man-Made Disaster / /

IndustryTerm

online computation / online / tree search / real-time demonstration / less search / search procedure / food pellet / food pellets / Online policy improvement using Monte-Carlo search / search algorithm / search heuristics / search methods / food / control algorithm / rollout algorithm / observable algorithm / search trees / online planning algorithms / depth-first search / forward search / online planners / online algorithm / search tree / prior online planning methods / search space / Online POMDP planners / search value iteration / search time / /

Organization

MIT / /

Person

David Silver / Bt / Game Playing / /

/

Position

hb / rt / General / return Rt / first general purpose planner / offline full-width planner / offline planner / /

PublishedMedium

Machine Learning / Journal of Artificial Intelligence Research / /

Technology

online algorithm / search algorithm / UCB1 algorithm / UCT algorithm / control algorithm / POMCP algorithm / Machine Learning / 4 Convergence The UCT algorithm / PO-rollout algorithm / Rollout algorithms / online planning algorithms / 4 Algorithm / Monte-Carlo algorithm / rollout algorithm / partially observable UCT algorithm / simulation / MonteCarlo planning algorithm / /

URL

http /

SocialTag