Sciweavers

56 search results - page 3 / 12
» Learning a Fast Emulator of a Binary Decision Process
Sort
View
ICML
2003
IEEE
14 years 8 months ago
The Cross Entropy Method for Fast Policy Search
We present a learning framework for Markovian decision processes that is based on optimization in the policy space. Instead of using relatively slow gradient-based optimization al...
Shie Mannor, Reuven Y. Rubinstein, Yohai Gat
ICML
2006
IEEE
14 years 8 months ago
Fast direct policy evaluation using multiscale analysis of Markov diffusion processes
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
JDCTA
2010
160views more  JDCTA 2010»
13 years 2 months ago
Learning and Decision Making in Human During a Game of Matching Pennies
To gain insights into the neural basis of such adaptive decision-making processes, we investigated the nature of learning process in humans playing a competitive game with binary ...
Jianfeng Hu, Xiaofeng Li, Jinghai Yin
TCSV
2008
139views more  TCSV 2008»
13 years 7 months ago
A Fast MB Mode Decision Algorithm for MPEG-2 to H.264 P-Frame Transcoding
Abstract--The H.264 standard achieves much higher coding efficiency than the MPEG-2 standard, due to its improved inter-and intra-prediction modes at the expense of higher computat...
Gerardo Fernández-Escribano, Hari Kalva, Pe...
CORR
2006
Springer
109views Education» more  CORR 2006»
13 years 7 months ago
On Conditional Branches in Optimal Decision Trees
The decision tree is one of the most fundamental ing abstractions. A commonly used type of decision tree is the alphabetic binary tree, which uses (without loss of generality) &quo...
Michael B. Baer