Sciweavers

1997 search results - page 194 / 400
» On the convergence of Hill's method
Sort
View
NIPS
2001
15 years 2 months ago
MIME: Mutual Information Minimization and Entropy Maximization for Bayesian Belief Propagation
Bayesian belief propagation in graphical models has been recently shown to have very close ties to inference methods based in statistical physics. After Yedidia et al. demonstrate...
Anand Rangarajan, Alan L. Yuille
UAI
2000
15 years 2 months ago
Fast Planning in Stochastic Games
Stochastic games generalize Markov decision processes MDPs to a multiagent setting by allowing the state transitions to depend jointly on all player actions, and having rewards de...
Michael J. Kearns, Yishay Mansour, Satinder P. Sin...
CORR
2010
Springer
127views Education» more  CORR 2010»
15 years 1 months ago
Mean field for Markov Decision Processes: from Discrete to Continuous Optimization
We study the convergence of Markov Decision Processes made of a large number of objects to optimization problems on ordinary differential equations (ODE). We show that the optimal...
Nicolas Gast, Bruno Gaujal, Jean-Yves Le Boudec
HEURISTICS
2008
120views more  HEURISTICS 2008»
15 years 1 months ago
A local linear embedding module for evolutionary computation optimization
A Local Linear Embedding (LLE) module enhances the performance of two Evolutionary Computation (EC) algorithms employed as search tools in global optimization problems. The LLE em...
Fabio Boschetti
CCE
2007
15 years 1 months ago
A systematic approach to plant-wide control based on thermodynamics
In this work, a systematic approach to plant-wide control design is proposed. The method combines ingredients from process networks, thermodynamics and systems theory to derive ro...
Luis T. Antelo, Irene Otero-Muras, Julio R. Banga,...