Regret Bounds for Stochastic Combinatorial Multi-Armed Bandits with Linear Space Complexity.

Mridul Agarwal Vaneet Aggarwal

Published in: CoRR (2018)

Keyphrases

multi armed bandit
space complexity
multi armed bandits
regret bounds
online learning
lower bound
linear regression
worst case
upper bound
arc consistency
reinforcement learning
special case
bregman divergences