… for heavy-tailed bandits, we first propose a new quantum … for heavy-tailed distributions,
which is based on the Quantum … quantum mean estimator, we focus on quantum heavy-tailed …

… In this paper, we generalize the concept of heavytailed multi-armed bandits … heavy-tailed
bandits in both stochastic and adversarial cases. In contrast to existing (stochastic) heavy-tailed …

… the UCB algorithm to heavytailed stochastic multi-armed bandit problems in which the …
heavytailed bandits with dependent reward processes. While we focused our attention on bandit …

… The median-of-means estimator is a commonly-used strategy for performing robust mean
estimation in heavy-tailed bandit algorithms. In an orthogonal line of work, Pazis et al. [2016] …

… approaches to introduce quantum bandit algorithms for, respectively, stochastic convex
bandits and bandits with heavy-tailed reward distributions. In addition to quantum bandits, some …

… quantum computing and the demonstrated success of quantum Monte Carlo in simpler bandit
… [43] extended this line of research to quantum bandits with heavy-tailed rewards, while [25] …

… the quantum information feedback from these quantum systems can be leveraged to improve
the learning efficiency. In this paper, we study the BAI problem in quantum … Quantum bandit …

… quantum algorithm for estimating the mean of a real-valued random variable obtained as
the output of a quantum … to estimate the mean of a heavy-tailed distribution with a sub-Gaussian …

… We will consider a much more powerful fully adaptive adversary in the next section on
linear-contextual bandits. We note that although algorithms for heavy-tailed bandits can handle …

… parameterize policies as heavy-tailed distributions, which induces heavy-tailed gradient
noise. … • We present a few heavy-tailed policy parameterizations that may be used in lieu of a …