1227 search results - page 46 / 246 » Learning Rates for Q-Learning |
138
click to vote
COLT
2008
Springer
15 years 7 months ago
2008
Springer
We propose a model-based learning algorithm, the Adaptive Aggregation Algorithm (AAA), that aims to solve the online, continuous state space reinforcement learning problem in a de...
139
click to vote
NIPS
2007
15 years 7 months ago
2007
Can we leverage learning techniques to build a fast nearest-neighbor (ANN) retrieval data structure? We present a general learning framework for the NN problem in which sample que...
133
click to vote
JCP
2006
15 years 6 months ago
2006
Compared with conventional two-class learning schemes, one-class classification simply uses a single class in the classifier training phase. Applying one-class classification to le...
175
click to vote
NLP
2000
15 years 9 months ago
2000
Abstract. The paper argues that a promising way to improve the success rate of preference-based anaphora resolution algorithms is the use of machine learning. The paper outlines MA...
142
click to vote
MLMI
2005
Springer
15 years 11 months ago
2005
Springer
We show that, using a Support Vector Machine classifier, it is possible to determine with a 75% success rate who dominated a particular meeting on the basis of a few basic feature...