Sciweavers

9841 search results - page 227 / 1969
» Distributed Value Functions
Sort
View
TOMACS
2010
79views more  TOMACS 2010»
15 years 29 days ago
A stochastic approximation method with max-norm projections and its applications to the Q-learning algorithm
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...
Sumit Kunnumkal, Huseyin Topaloglu
VLDB
2007
ACM
141views Database» more  VLDB 2007»
16 years 6 months ago
Query Processing over Incomplete Autonomous Databases
Incompleteness due to missing attribute values (aka "null values") is very common in autonomous web databases, on which user accesses are usually supported through media...
Garrett Wolf, Hemal Khatri, Bhaumik Chokshi, Jianc...
COLT
2010
Springer
15 years 4 months ago
Optimal Algorithms for Online Convex Optimization with Multi-Point Bandit Feedback
Bandit convex optimization is a special case of online convex optimization with partial information. In this setting, a player attempts to minimize a sequence of adversarially gen...
Alekh Agarwal, Ofer Dekel, Lin Xiao
160
Voted
CPHYSICS
2008
90views more  CPHYSICS 2008»
15 years 6 months ago
Optimum bias for fast-switching free energy calculations
We derive the bias function that minimizes the statistical error of free energy differences calculated in work-biased fast-switching simulations. The optimum bias function is comp...
Harald Oberhofer, Christoph Dellago
MSS
2008
IEEE
88views Hardware» more  MSS 2008»
15 years 6 months ago
Maximizing an interval order on compact subsets of its domain
Maximal elements of a binary relation on compact subsets of a metric space define a choice function. An infinite extension of transitivity is necessary and sufficient for such a c...
Nikolai S. Kukushkin