Back to Results
First PageMeta Content
Monte Carlo methods / Computational statistics / Importance sampling / Variance reduction / Pi / Logarithm / Hidden Markov model / Reinforcement learning / Markov models / Mathematical analysis / Mathematics


Importance Sampling Estimates for Policies with Memory Christian R. Shelton MIT, AI Lab 545 Technology Square, NE43-741, Cambridge, MAUSA Abstract
Add to Reading List

Document Date: 2003-05-27 20:51:52

Open Document

File Size: 150,95 KB

Share Result on Facebook

City

Cambridge / /

Company

N. & Kaelbling L. P. / John Wiley & Sons / /

/

Facility

Technology Square / /

IndustryTerm

importance sampling greedy-search algorithm / Linear time algorithms / particular importance sampling algorithm / reinforcement learning algorithm / dataefficient algorithms / learning algorithm / /

Organization

AI Lab / MIT / /

Person

Christian R. Shelton / /

Position

rT / finite-state controller / /

ProvinceOrState

Massachusetts / /

PublishedMedium

Machine Learning / /

Technology

importance sampling greedy-search algorithm / learning algorithm / speech recognition / Machine Learning / Simulation / reinforcement learning algorithm / artificial intelligence / one particular importance sampling algorithm / Linear time algorithms / dataefficient algorithms / 545 Technology / /

SocialTag