Almost Optimal Algorithms for Linear Stochastic Bandits with Heavy-Tailed Payoffs.

Han Shao Xiaotian Yu Irwin King Michael R. Lyu

Published in: CoRR (2018)

Keyphrases

heavy tailed
regret bounds
computational complexity
multi armed bandit
learning algorithm
worst case
bayesian networks
higher order
mutual information
closed form
probability density function