Sciweavers

Share
7 search results - page 1 / 2
» Algorithms for Infinitely Many-Armed Bandits
Sort
View
NIPS
2008
11 years 3 months ago
Algorithms for Infinitely Many-Armed Bandits
We consider multi-armed bandit problems where the number of arms is larger than the possible number of experiments. We make a stochastic assumption on the mean-reward of a new sel...
Yizao Wang, Jean-Yves Audibert, Rémi Munos
CORR
2006
Springer
140views Education» more  CORR 2006»
11 years 1 months ago
Nearly optimal exploration-exploitation decision thresholds
While in general trading off exploration and exploitation in reinforcement learning is hard, under some formulations relatively simple solutions exist. Optimal decision thresholds ...
Christos Dimitrakakis
STOC
2007
ACM
146views Algorithms» more  STOC 2007»
12 years 1 months ago
Playing games with approximation algorithms
In an online linear optimization problem, on each period t, an online algorithm chooses st S from a fixed (possibly infinite) set S of feasible decisions. Nature (who may be adve...
Sham M. Kakade, Adam Tauman Kalai, Katrina Ligett
CORR
2010
Springer
189views Education» more  CORR 2010»
11 years 1 months ago
An Optimal Dynamic Mechanism for Multi-Armed Bandit Processes
We consider the problem of revenue-optimal dynamic mechanism design in settings where agents' types evolve over time as a function of their (both public and private) experien...
Sham M. Kakade, Ilan Lobel, Hamid Nazerzadeh
NIPS
2004
11 years 3 months ago
Nearly Tight Bounds for the Continuum-Armed Bandit Problem
In the multi-armed bandit problem, an online algorithm must choose from a set of strategies in a sequence of n trials so as to minimize the total cost of the chosen strategies. Wh...
Robert D. Kleinberg
books