2011 search results - page 202 / 403 » Universal Reinforcement Learning |
132
click to vote
ICML
2008
IEEE
16 years 5 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...
123
click to vote
ICML
2001
IEEE
16 years 5 months ago
2001
IEEE
We call data weakly labeled if it has no exact label but rather a numerical indication of correctness of the label "guessed" by the learning algorithm - a situation comm...
171
Voted
ATAL
2005
Springer
15 years 10 months ago
2005
Springer
We present an integrated approach for reasoning about and learning conversation patterns in multiagent communication. The approach is based on the assumption that information abou...
129
click to vote
AUSAI
2008
Springer
15 years 7 months ago
2008
Springer
Learning Classifier System (LCS) is an effective tool to solve classification problems. Clustering with XCS (accuracy-based LCS) is a novel approach proposed recently. In this pape...
129
click to vote
NIPS
2004
15 years 6 months ago
2004
We propose a probabilistic, generative account of configural learning phenomena in classical conditioning. Configural learning experiments probe how animals discriminate and gener...