Online multi-armed bandits with adaptive inference
M Dimakopoulou, Z Ren… - Advances in Neural …, 2021 - proceedings.neurips.cc
During online decision making in Multi-Armed Bandits (MAB), one needs to conduct
inference on the true mean reward of each arm based on data collected so far at each step …
inference on the true mean reward of each arm based on data collected so far at each step …
Multi-armed bandit experimental design: Online decision-making and adaptive inference
D Simchi-Levi, C Wang - International Conference on …, 2023 - proceedings.mlr.press
Multi-armed bandit has been well-known for its efficiency in online decision-making in terms
of minimizing the loss of the participants' welfare during experiments (ie, the regret). In …
of minimizing the loss of the participants' welfare during experiments (ie, the regret). In …
Are sample means in multi-armed bandits positively or negatively biased?
It is well known that in stochastic multi-armed bandits (MAB), the sample mean of an arm is
typically not an unbiased estimator of its true mean. In this paper, we decouple three …
typically not an unbiased estimator of its true mean. In this paper, we decouple three …
A closer look at the worst-case behavior of multi-armed bandit algorithms
One of the key drivers of complexity in the classical (stochastic) multi-armed bandit (MAB)
problem is the difference between mean rewards in the top two arms, also known as the …
problem is the difference between mean rewards in the top two arms, also known as the …
Causal bandits: Online decision-making in endogenous settings
The deployment of Multi-Armed Bandits (MAB) has become commonplace in many
economic applications. However, regret guarantees for even state-of-the-art linear bandit …
economic applications. However, regret guarantees for even state-of-the-art linear bandit …
Sub-sampling for multi-armed bandits
The stochastic multi-armed bandit problem is a popular model of the exploration/exploitation
trade-off in sequential decision problems. We introduce a novel algorithm that is based on …
trade-off in sequential decision problems. We introduce a novel algorithm that is based on …
Scaling multi-armed bandit algorithms
The Multi-Armed Bandit (MAB) is a fundamental model capturing the dilemma between
exploration and exploitation in sequential decision making. At every time step, the decision …
exploration and exploitation in sequential decision making. At every time step, the decision …
Counterfactual data-fusion for online reinforcement learners
Abstract The Multi-Armed Bandit problem with Unobserved Confounders (MABUC)
considers decision-making settings where unmeasured variables can influence both the …
considers decision-making settings where unmeasured variables can influence both the …
Stochastic rising bandits
This paper is in the field of stochastic Multi-Armed Bandits (MABs), ie, those sequential
selection techniques able to learn online using only the feedback given by the chosen …
selection techniques able to learn online using only the feedback given by the chosen …
An experimental design for anytime-valid causal inference on multi-armed bandits
Typically, multi-armed bandit (MAB) experiments are analyzed at the end of the study and
thus require the analyst to specify a fixed sample size in advance. However, in many online …
thus require the analyst to specify a fixed sample size in advance. However, in many online …