Sciweavers

ICML
2006
IEEE

143views Machine Learning» more ICML 2006»

Fast direct policy evaluation using multiscale analysis of Markov diffusion processes

14 years 5 months ago

Policy evaluation is a critical step in the approximate solution of large Markov decision processes (MDPs), typically requiring O(|S|3 ) to directly solve the Bellman system of |S...

Mauro Maggioni, Sridhar Mahadevan

claim paper

Read More »

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers