We propose EB-TC $\varepsilon $, a novel sampling rule for $\varepsilon $-best arm
identification in stochastic bandits. It is the first instance of Top Two algorithm analyzed for …

A Top Two sampling rule for bandit identification is a method which selects the next arm to
sample from among two candidate arms, a leader and a challenger. Due to their simplicity …

This paper studies the fixed-confidence best arm identification (BAI) problem in the bandit
framework in the canonical single-parameter exponential models. For this problem, many …

Abstract Best Arm Identification (BAI) problems are progressively used for data-sensitive
applications, such as designing adaptive clinical trials, tuning hyper-parameters, and …

We study the problem of best-arm identification (BAI) in the fixed-budget setting with
heterogeneous reward variances. We propose two variance-adaptive BAI algorithms for this …

Most bandit algorithms assume that the reward variances or their upper bounds are known,
and that they are the same for all arms. This naturally leads to suboptimal performance and …

We address the problem of best arm identification (BAI) with a fixed budget for two-armed
Gaussian bandits. In BAI, given multiple arms, we aim to find the best arm, an arm with the …

In this paper, we study reinforcement learning from human feedback (RLHF) under an
episodic Markov decision process with a general trajectory-wise reward model. We …

Best Arm Identification (BAI) problems are progressively used for data-sensitive applications,
such as designing adaptive clinical trials, tuning hyper-parameters, and conducting user …

We consider the problem of best arm identification in the multi-armed bandit model, under
fixed confidence. Given a confidence input δ, the goal is to identify the arm with the highest …