495 search results - page 16 / 99 » Constructing States for Reinforcement Learning |
ICML
2008
IEEE
14 years 8 months ago
2008
IEEE
We present an algorithm, HI-MAT (Hierarchy Induction via Models And Trajectories), that discovers MAXQ task hierarchies by applying dynamic Bayesian network models to a successful...
ROBOCUP
2007
Springer
14 years 1 months ago
2007
Springer
The existing reinforcement learning approaches have been suffering from the curse of dimension problem when they are applied to multiagent dynamic environments. One of the typical...
ATAL
2004
Springer
14 years 1 months ago
2004
Springer
This paper presents a reinforcement learning algorithm used to allocate tasks to agents in an uncertain real-time environment. In such environment, tasks have to be analyzed and a...
ECML
2003
Springer
14 years 29 days ago
2003
Springer
Due to the unavoidable fact that a robot’s sensors will be limited in some manner, it is entirely possible that it can find itself unable to distinguish between differing state...
IWANN
1999
Springer
13 years 12 months ago
1999
Springer
To avoid the curse of dimensionality, function approximators are used in reinforcement learning to learn value functions for individual states. In order to make better use of comp...