45 search results - page 7 / 9 » Expected Convergence Properties of BGP |
WSC
2001
13 years 9 months ago
2001
We address performance issues associated with simulationbased algorithms for optimizing Markov reward processes. Specifically, we are concerned with algorithms that exploit the re...
AAAI
1998
13 years 9 months ago
1998
A central problem in learning in complex environmentsis balancing exploration of untested actions against exploitation of actions that are known to be good. The benefit of explora...
CORR
2010
Springer
13 years 4 months ago
2010
Springer
Ensuring sufficient liquidity is one of the key challenges for designers of prediction markets. Various market making algorithms have been proposed in the literature and deployed ...
TOMACS
2010
13 years 2 months ago
2010
In this paper, we develop a stochastic approximation method to solve a monotone estimation problem and use this method to enhance the empirical performance of the Q-learning algor...
ICML
2004
IEEE
14 years 8 months ago
2004
IEEE
Boosting is a popular approach for building accurate classifiers. Despite the initial popular belief, boosting algorithms do exhibit overfitting and are sensitive to label noise. ...