361 search results - page 6 / 73 » Approximate counting by dynamic programming |
CORR
2010
Springer
13 years 7 months ago
2010
Springer
In this paper, we consider the problem of planning and learning in the infinite-horizon discounted-reward Markov decision problems. We propose a novel iterative direct policysearc...
NIPS
2008
13 years 9 months ago
2008
Most algorithms for solving Markov decision processes rely on a discount factor, which ensures their convergence. It is generally assumed that using an artificially low discount f...
JCP
2007
13 years 7 months ago
2007
Abstract— We describe a general method to transform a non-Markovian sequential decision problem into a supervised learning problem using a K-bestpaths algorithm. We consider an a...
ICML
1995
IEEE
14 years 8 months ago
1995
IEEE
The success ofreinforcement learninginpractical problems depends on the ability to combine function approximation with temporal di erence methods such as value iteration. Experime...
HICSS
2009
IEEE
14 years 2 months ago
2009
IEEE
One knowledge discovery problem in the rapid response setting is the cost of learning which patterns are indicative of a threat. This typically involves a detailed follow-through,...