# Tracking the Best Expert in Non-stationary Stochastic Environments

Chen-Yu WeiYi-Te HongChi-Jen Lu

We study the dynamic regret of multi-armed bandit and experts problem in non-stationary stochastic environments. We introduce a new parameter $\Lambda$, which measures the total statistical variance of the loss distributions over $T$ rounds of the process, and study how this amount affects the regret... (read more)

PDF Abstract

# Code Add Remove

No code implementations yet. Submit your code now