arXiv research

Paper improves CMAB regret bounds by reducing batch-size dependency.

This paper extends the MAB problem to consider risk-reward tradeoffs.

Thompson Sampling is at most twice as bad as any other policy in Bayesian bandit models.

Paper tackles identifying an odd arm in a multi-armed bandit with restless Markov processes and trembling hand.

Improved best-arm identification in correlated multi-armed bandits.

We consider a problem of stochastic online learning with general probabilistic graph feedback, where each directed edge in the feedback graph has probability $p_{ij}$. Two cases are covered. (a) The one-step case, where after playing arm $i$ the learner observes a sample reward feedback of arm $j$ with independent prob…

In this paper, we study the combinatorial multi-armed bandit problem (CMAB) with probabilistically triggered arms (PTAs). Under the assumption that the arm triggering probabilities (ATPs) are positive for all arms, we prove that a class of upper confidence bound (UCB) policies, named Combinatorial UCB with exploration …

New algorithm finds best feasible arm in grouped bandits.

We address the M-best-arm identification problem in multi-armed bandits. A player has a limited budget to explore K arms (M<K), and once pulled, each arm yields a reward drawn (independently) from a fixed, unknown distribution. The goal is to find the top M arms in the sense of expected reward. We develop an algorithm …

New algorithms ensure fair selection in combinatorial semi-bandit with unrestricted delays.

We consider the best-arm identification problem in multi-armed bandits, which focuses purely on exploration. A player is given a fixed budget to explore a finite set of arms, and the rewards of each arm are drawn independently from a fixed, unknown distribution. The player aims to identify the arm with the largest expe…

New algorithms identify best arm with less pulls, adapting to arm covariances.

The paper tackles resource allocation for arms with unknown and random rewards, achieving optimal regret bounds.

We analyze the $K$-armed bandit problem where the reward for each arm is a noisy realization based on an observed context under mild nonparametric assumptions. We attain tight results for top-arm identification and a sublinear regret of $\widetilde{O}\Big(T^{\frac{1+D}{2+D}}\Big)$, where $D$ is the context dimension, f…

We study the stochastic multi-armed bandit problem in the case when the arm samples are dependent over time and generated from so-called weak $\cC$-mixing processes. We establish a $\cC-$Mix Improved UCB agorithm and provide both problem-dependent and independent regret analysis in two different scenarios. In the first…

New algorithm for countable bandits with optimal regret.

ARMS improves gradient estimation for binary variables using antithetic samples.

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

Study best arm identification in restless Markov multi-armed bandits with state-dependent transitions.

Unified meta algorithms estimate various distribution functionals in infinite-armed bandits.

We consider the combinatorial multi-armed bandit (CMAB) problem, where the reward function is nonlinear. In this setting, the agent chooses a batch of arms on each round and receives feedback from each arm of the batch. The reward that the agent aims to maximize is a function of the selected arms and their expectations…

We study how the regret guarantees of nonstochastic multi-armed bandits can be improved, if the effective range of the losses in each round is small (e.g. the maximal difference between two losses in a given round). Despite a recent impossibility result, we show how this can be made possible under certain mild addition…

New model for multi-armed bandits with growing arms.

Study best arm identification in restless bandits with unknown TPMs.

Adaptive algorithms minimize regret in matching markets with contextual arm preferences.

EgalMAB solves fair resource allocation in stochastic bandits.

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

New bandit problem for finding best group of arms with worst mean reward.

New algorithm tackles stochastic bandits with varying arm-dependent delays.

This paper extends combinatorial semi-bandits to graph feedback, improving regret bounds.

Optimal best arm identification for multi-objective bandits with fixed error probability.

Study on bandit problem with fixed number of arm types, achieving optimal regret bounds.

Algorithm identifies best arm in bandit game with variance consideration.

In this paper, we introduce a new online decision making paradigm that we call Thresholding Graph Bandits. The main goal is to efficiently identify a subset of arms in a multi-armed bandit problem whose means are above a specified threshold. While traditionally in such problems, the arms are assumed to be independent, …

Proposes a new semi-parametric framework for batched bandits with covariates.

We consider stochastic multi-armed bandit problems with complex actions over a set of basic arms, where the decision maker plays a complex action rather than a basic arm in each round. The reward of the complex action is some function of the basic arms' rewards, and the feedback observed may not necessarily be the rewa…

The paper tackles noisy multi-armed bandit problems with improved regret guarantees.

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 algorithm reduces regret in multi-agent bandits with malicious agents.

In this paper, we investigate the impact of diverse user preference on learning under the stochastic multi-armed bandit (MAB) framework. We aim to show that when the user preferences are sufficiently diverse and each arm can be optimal for certain users, the O(log T) regret incurred by exploring the sub-optimal arms un…

New model for display advertising with stochastic and adversarial components.

Opt-BBAI identifies the best arm with minimal batches and pulls, optimizing both sample and batch complexity.

Optimal top-2 method improves best arm identification with reduced error.

Optimal resource allocation in censored semi-bandits with unknown thresholds.

The paper improves bandit algorithms by incorporating random-effect models.

Optimal algorithm for latent bandits with cluster structure reduces regret to nearly optimal.

New bounds for bandits with graph feedback, improving previous results.

We consider the restless Markov bandit problem, in which the state of each arm evolves according to a Markov process independently of the learner's actions. We suggest an algorithm that after $T$ steps achieves $\tilde{O}(\sqrt{T})$ regret with respect to the best policy that knows the distributions of all arms. No ass…