arXiv research

Study quantile multi-armed bandits for identifying the best arm with a specified quantile level.

Study quantile reward identification with 1-bit feedback constraints.

A robust bandit algorithm uses Dirichlet sampling to minimize regret under various distributional assumptions.

We propose confidence sequences -- sequences of confidence intervals which are valid uniformly over time -- for quantiles of any distribution over a complete, fully-ordered set, based on a stream of i.i.d. observations. We give methods both for tracking a fixed quantile and for tracking all quantiles simultaneously. Sp…

We consider a multi-armed bandit problem with covariates. Given a realization of the covariate vector, instead of targeting the treatment with highest conditional expectation, the decision maker targets the treatment which maximizes a general functional of the conditional potential outcome distribution, e.g., a conditi…

New dynamic allocation methods for multi-armed bandit models.

PAC-Bayesian analysis improves lifelong learning in multi-armed bandits.

Paper uses subjective logic to estimate uncertainty in multi-armed bandit problems.

Algorithm improves multi-armed bandit performance by transferring reward samples.

Quantum algorithms for multi-armed bandits are explored with limited reward access.

Study on Pareto optimality in multi-objective bandit problems.

Unified formulation bridges adversarial and nonstationary bandits.

In this paper we propose a multi-armed bandit inspired, pool based active learning algorithm for the problem of binary classification. By carefully constructing an analogy between active learning and multi-armed bandits, we utilize ideas such as lower confidence bounds, and self-concordant regularization from the multi…

Study finds optimal regret bound for multi-armed bandit problem with expert advice.

The paper tackles lifelong learning in multi-armed bandits, aiming to minimize average regret over multiple tasks.

This note gives a short, self-contained, proof of a sharp connection between Gittins indices and Bayesian upper confidence bound algorithms. I consider a Gaussian multi-armed bandit problem with discount factor $γ$. The Gittins index of an arm is shown to equal the $γ$-quantile of the posterior distribution of the arm'…

We consider the stochastic linear (multi-armed) contextual bandit problem with the possibility of hidden simple multi-armed bandit structure in which the rewards are independent of the contextual information. Algorithms that are designed solely for one of the regimes are known to be sub-optimal for the alternate regime…

New method for identifying best arm in batched multi-armed bandit problems.

Study collaborative learning among multi-agents in multi-armed bandits.

The paper explores sampling problems and shows minimal exploration is needed.

New algorithm for nonstationary multi-armed bandits with optimal performance.

Paper tackles transfer learning for contextual multi-armed bandits under covariate shift.

Proposes Genetic Thompson Sampling for multi-armed bandits, improving performance in nonstationary settings.

New method for contextual bandits with corrupted context.

We present a formal model of human decision-making in explore-exploit tasks using the context of multi-armed bandit problems, where the decision-maker must choose among multiple options with uncertain rewards. We address the standard multi-armed bandit problem, the multi-armed bandit problem with transition costs, and …

In this paper, we study the multi-armed bandit problem in the batched setting where the employed policy must split data into a small number of batches. While the minimax regret for the two-armed stochastic bandits has been completely characterized in \cite{perchet2016batched}, the effect of the number of arms on the re…

Sequential portfolio selection has attracted increasing interests in the machine learning and quantitative finance communities in recent years. As a mathematical framework for reinforcement learning policies, the stochastic multi-armed bandit problem addresses the primary difficulty in sequential decision making under …

In recent years, multi-armed bandit (MAB) framework has attracted a lot of attention in various applications, from recommender systems and information retrieval to healthcare and finance, due to its stellar performance combined with certain attractive properties, such as learning from less feedback. The multi-armed ban…

New algorithm prevents strategic replication in multi-armed bandit problems.

This paper applies Thompson Sampling to asymmetric $\alpha$-stable bandits for financial and wireless data.

The paper examines how loss aversion impacts multi-armed bandit decisions over long periods.

Two non-communicating players minimize regret in a multi-armed bandit game.

The study uses a multi-armed bandit model to analyze and mitigate hiring discrimination.

Gittins indices provide an optimal solution to the classical multi-armed bandit problem. An obstacle to their use has been the common perception that their computation is very difficult. This paper demonstrates an accessible general methodology for the calculating Gittins indices for the multi-armed bandit with a detai…

A new federated multi-armed bandit framework with personalization balances generalization and personalization.

The paper connects discrete choice models to multi-armed bandit algorithms with sublinear regret bounds.

Multi-armed bandits are a quintessential machine learning problem requiring the balancing of exploration and exploitation. While there has been progress in developing algorithms with strong theoretical guarantees, there has been less focus on practical near-optimal finite-time performance. In this paper, we propose an …

DPPS uses DP priors for Bayesian non-parametric multi-arm bandits.

The paper tackles a bandit problem with infinitely many arms per group, aiming to identify the group with the highest quantile reward.

A new algorithm for resource-aware multi-armed bandits minimizes regret.

Study on indexability of restless multi-armed bandits and rollout policy performance.

An optimal algorithm for multi-armed bandits with constraints.

This work explores the idea of a causal contextual multi-armed bandit approach to automated marketing, where we estimate and optimize the causal (incremental) effects. Focusing on causal effect leads to better return on investment (ROI) by targeting only the persuadable customers who wouldn't have taken the action orga…

New lower bounds for combinatorial multi-armed bandits for general reward functions.

The paper honors Lai's contributions to multi-armed bandits and establishes new regret bounds.

New algorithms solve complex function optimization problems.

Study on information evolution in interactive decision making using multi-armed bandits.

Kernel $ε$-Greedy optimizes multi-armed bandits with covariates for sub-linear regret.