Perturbed-History Exploration in Stochastic Linear Bandits.

Branislav Kveton Csaba Szepesvári Mohammad Ghavamzadeh Craig Boutilier

Published in: CoRR (2019)

Keyphrases

stochastic systems
regret bounds
real time
piecewise linear
stochastic model
reinforcement learning
original data
stochastic processes
stochastic optimization