arXiv research

Study on Pareto optimality in multi-objective bandit problems.

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

We consider the problem of minimizing the regret in stochastic multi-armed bandit, when the measure of goodness of an arm is not the mean return, but some general function of the mean and the variance.We characterize the conditions under which learning is possible and present examples for which no natural algorithm can…

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

New algorithm uses control variates to improve multi-armed bandit performance.

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…

The study analyzes batched methods for early stopping in stochastic multi-armed bandits.

New insights into balancing reward and fairness in stochastic MAB.

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

Adaptive and sequential experiment design is a well-studied area in numerous domains. We survey and synthesize the work of the online statistical learning paradigm referred to as multi-armed bandits integrating the existing research as a resource for a certain class of online experiments. We first explore the tradition…

New algorithm optimizes multi-armed bandit performance in stochastic and adversarial settings.

New model for display advertising with stochastic and adversarial components.

Paper tackles good arm identification in stochastic bandits.

We study the stochastic multi-armed bandit problem when one knows the value $μ^{(\star)}$ of an optimal arm, as a well as a positive lower bound on the smallest positive gap $Δ$. We propose a new randomized policy that attains a regret {\em uniformly bounded over time} in this setting. We also prove several lower bound…

Improved FTRL algorithm for multi-armed bandits with various regularizers and multiple optimal arms.

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 …

We consider the non-stochastic version of the (cooperative) multi-player multi-armed bandit problem. The model assumes no communication at all between the players, and furthermore when two (or more) players select the same action this results in a maximal loss. We prove the first $\sqrt{T}$-type regret guarantee for th…

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

Study on individual regret in cooperative MAB with agents communicating over a graph.

INF-clip optimizes heavy-tailed MAB problems with improved performance.

We investigate the optimality of perturbation based algorithms in the stochastic and adversarial multi-armed bandit problems. For the stochastic case, we provide a unified regret analysis for both sub-Weibull and bounded perturbations when rewards are sub-Gaussian. Our bounds are instance optimal for sub-Weibull pertur…

The paper studies MAB problems with LDP to balance privacy and service quality.

Adaptive MAB algorithms handle composite, anonymous feedback without reward interval knowledge.

New algorithm reduces memory-regret trade-off for bandits.

Paper develops robust estimators and strategies for stochastic MABs with heavy-tailed rewards.

New study on regret lower bounds for multi-agent multi-armed bandit problems.

A new framework for risk-aware multi-armed bandits tackles volatile environments.

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

Maximin UCB algorithm optimizes energy harvesting for sensor networks.

This paper analyzes the multi-armed bandit model using path-integral methods.

Algorithm optimizes a single attribute in multi-armed bandits with constraints.

We propose an online algorithm for cumulative regret minimization in a stochastic multi-armed bandit. The algorithm adds $O(t)$ i.i.d. pseudo-rewards to its history in round $t$ and then pulls the arm with the highest average reward in its perturbed history. Therefore, we call it perturbed-history exploration (PHE). Th…

In this paper, we propose an information-theoretic exploration strategy for stochastic, discrete multi-armed bandits that achieves optimal regret. Our strategy is based on the value of information criterion. This criterion measures the trade-off between policy information and obtainable rewards. High amounts of policy …

New algorithm tackles unknown utility network resource allocation.

New algorithm ensures replicable results in multi-armed bandits with minimal extra regret.

We study the stochastic multi-armed bandits problem in the presence of adversarial corruption. We present a new algorithm for this problem whose regret is nearly optimal, substantially improving upon previous work. Our algorithm is agnostic to the level of adversarial contamination and can tolerate a significant amount…

This paper is devoted to regret lower bounds in the classical model of stochastic multi-armed bandit. A well-known result of Lai and Robbins, which has then been extended by Burnetas and Katehakis, has established the presence of a logarithmic bound for all consistent policies. We relax the notion of consistence, and e…

Study shows how repetition affects learning in bandit settings, providing algorithms with sublinear regret.

New bandit model for e-commerce with ordered categories.

A new multi-armed bandit framework with credal sets for uncertain outcomes.

New strategy achieves optimal regret without communication or collisions in multi-player bandit.

New algorithms for streaming bandits with limited memory.

Optimism stabilizes Thompson Sampling for adaptive inference in multi-armed bandits.

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

Multi-armed bandit problems are the most basic examples of sequential decision problems with an exploration-exploitation trade-off. This is the balance between staying with the option that gave highest payoffs in the past and exploring new options that might give higher payoffs in the future. Although the study of band…

Sequential screening and dynamic regret in multi-armed bandits with arriving arms