Tuning Bandit Algorithms in Stochastic Environments.

Jean-Yves Audibert Rémi Munos Csaba Szepesvári

Published in: ALT (2007)

Keyphrases

recently developed
orders of magnitude
computational cost
neural network
significant improvement
parameter tuning
data structure
learning algorithm
reinforcement learning
database systems
search engine
state space
worst case
classification algorithm
real time
stochastic search
stochastic approximation