28 search results - page 1 / 6 » Partitioned Linear Programming Approximations for MDPs |
UAI
2008
13 years 6 months ago
2008
Approximate linear programming (ALP) is an efficient approach to solving large factored Markov decision processes (MDPs). The main idea of the method is to approximate the optimal...
NIPS
2003
13 years 6 months ago
2003
Approximate linear programming (ALP) has emerged recently as one of the most promising methods for solving complex factored MDPs with finite state spaces. In this work we show th...
AMAI
2006
Springer
13 years 4 months ago
2006
Springer
A weakness of classical Markov decision processes (MDPs) is that they scale very poorly due to the flat state-space representation. Factored MDPs address this representational pro...
AIPS
2006
13 years 6 months ago
2006
Markov decision processes (MDPs) with discrete and continuous state and action components can be solved efficiently by hybrid approximate linear programming (HALP). The main idea ...
JAIR
2006
13 years 4 months ago
2006
Efficient representations and solutions for large decision problems with continuous and discrete variables are among the most important challenges faced by the designers of automa...