92 search results - page 11 / 19 » Game-based Abstraction for Markov Decision Processes |
ML
2002
ACM
14 years 11 months ago
2002
ACM
Abstract. The problemof state abstractionis of centralimportancein optimalcontrol,reinforcement learning and Markov decision processes. This paper studies the case of variable reso...
158
click to vote
ILP
2007
Springer
15 years 5 months ago
2007
Springer
Abstract. Many reinforcement learning domains are highly relational. While traditional temporal-difference methods can be applied to these domains, they are limited in their capaci...
85
Voted
CDC
2008
IEEE
15 years 6 months ago
2008
IEEE
Abstract— Research on numerical solution methods for partially observable Markov decision processes (POMDPs) has primarily focused on discrete-state models, and these algorithms ...
SARA
2005
Springer
15 years 5 months ago
2005
Springer
Sets of features in Markov decision processes can play a critical role ximately representing value and in abstracting the state space. Selection of features is crucial to the succe...
100
Voted
ISLPED
1999
ACM
15 years 4 months ago
1999
ACM
-- The goal of a dynamic power management policy is to reduce the power consumption of an electronic system by putting system components into different states, each representing ce...