Sciweavers

263 search results - page 12 / 53
» Regret Bounds for Prediction Problems
Sort
View
TSP
2008
114views more  TSP 2008»
13 years 9 months ago
Universal Switching Linear Least Squares Prediction
We consider sequential regression of individual sequences under the square error loss. Using a competitive algorithm framework, we construct a sequential algorithm that can achieve...
Suleyman Serdar Kozat, Andrew C. Singer
CORR
2011
Springer
230views Education» more  CORR 2011»
13 years 4 months ago
Computational Rationalization: The Inverse Equilibrium Problem
Modeling the behavior of imperfect agents from a small number of observations is a difficult, but important task. In the singleagent decision-theoretic setting, inverse optimal co...
Kevin Waugh, Brian Ziebart, J. Andrew Bagnell
CORR
2010
Springer
174views Education» more  CORR 2010»
13 years 10 months ago
Gaussian Process Bandits for Tree Search
We motivate and analyse a new Tree Search algorithm, based on recent advances in the use of Gaussian Processes for bandit problems. We assume that the function to maximise on the ...
Louis Dorard, John Shawe-Taylor
COLT
2010
Springer
13 years 7 months ago
Open Loop Optimistic Planning
We consider the problem of planning in a stochastic and discounted environment with a limited numerical budget. More precisely, we investigate strategies exploring the set of poss...
Sébastien Bubeck, Rémi Munos
TIT
2002
89views more  TIT 2002»
13 years 9 months ago
Universal linear least squares prediction: Upper and lower bounds
We consider the problem of sequential linear prediction of real-valued sequences under the square-error loss function. For this problem, a prediction algorithm has been demonstrate...
Andrew C. Singer, Suleyman Serdar Kozat, Meir Fede...