arXiv research

Unified approach to correlated multi-armed bandits reduces regret significantly.

Improved control approach for correlated bandits with better performance.

Simplifies large action space bandits by selecting representative actions.

ARC algorithm optimizes dynamic pricing with correlated observations.

A new algorithm reduces suboptimal arm selection in correlated bandits.

While the objective in traditional multi-armed bandit problems is to find the arm with the highest mean, in many settings, finding an arm that best captures information about other arms is of interest. This objective, however, requires learning the underlying correlation structure and not just the means of the arms. Se…

New method uses correlated auxiliary feedback to reduce regret in parameterized bandits.

We consider the correlated multiarmed bandit (MAB) problem in which the rewards associated with each arm are modeled by a multivariate Gaussian random variable, and we investigate the influence of the assumptions in the Bayesian prior on the performance of the upper credible limit (UCL) algorithm and a new correlated U…

Proposes meTS for efficient exploration in correlated bandits.

New algorithm for partially observable contexts in finance.

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

A new algorithm for bandits with hierarchical rewards.

We consider a novel multi-armed bandit framework where the rewards obtained by pulling the arms are functions of a common latent random variable. The correlation between arms due to the common random source can be used to design a generalized upper-confidence-bound (UCB) algorithm that identifies certain arms as $non-c…

Unified Bayesian framework for efficient off-policy evaluation and learning in large action spaces.

Optimizing rewards under budget constraints with correlated costs and rewards.

AGG-UCB uses neural networks to optimize group behaviors in contextual bandits.

Contextual multi-armed bandit algorithms are widely used in sequential decision tasks such as news article recommendation systems, web page ad placement algorithms, and mobile health. Most of the existing algorithms have regret proportional to a polynomial function of the context dimension, $d$. In many applications ho…

New setting combines state evolution and corrupted context for better decision-making.

DART optimizes subset selection in non-linear bandit problems.

In this paper we consider the problem of online stochastic optimization of a locally smooth function under bandit feedback. We introduce the high-confidence tree (HCT) algorithm, a novel any-time $\mathcal{X}$-armed bandit algorithm, and derive regret bounds matching the performance of existing state-of-the-art in term…

Paper develops efficient algorithms for learning rationalizable equilibria in multiplayer games.

The medoid of a set of n points is the point in the set that minimizes the sum of distances to other points. It can be determined exactly in O(n^2) time by computing the distances between all pairs of points. Previous works show that one can significantly reduce the number of distance computations needed by adaptively …

We address the problem of finding the maximizer of a nonlinear smooth function, that can only be evaluated point-wise, subject to constraints on the number of permitted function evaluations. This problem is also known as fixed-budget best arm identification in the multi-armed bandit literature. We introduce a Bayesian …

First sample-efficient algorithm for learning EFCE in bandit feedback settings.

Characterizes UCB algorithm performance in bandit problems.

Paper introduces a bandit-learning method for multifidelity approximations.

Efficiently clusters noisy data with minimal queries.

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

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

We consider the problem of learning to play a repeated multi-agent game with an unknown reward function. Single player online learning algorithms attain strong regret bounds when provided with full information feedback, which unfortunately is unavailable in many real-world scenarios. Bandit feedback alone, i.e., observ…

Optimal algorithm for contextual bandits with unknown context distributions.

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

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 …

Study links cognitive effort to thermodynamic principles, optimizing decision-making.

The Knowledge Gradient (KG) policy was originally proposed for online ranking and selection problems but has recently been adapted for use in online decision making in general and multi-armed bandit problems (MABs) in particular. We study its use in a class of exponential family MABs and identify weaknesses, including …

Optimizes resource allocation for distributed parameter estimation in sensor networks.

Improves text classification on new domains using distance-based measures and dynamic domain selection.

A novel bandit problem with context-dependent rewards and blocking.

New algorithms boost SAT solver performance by optimizing restart strategies.

New testing method for robust actor-critic bandit algorithms.

New algorithm tackles nonstationary linear bandits with latent dynamics.

Motivated by online recommendation and advertising systems, we consider a causal model for stochastic contextual bandits with a latent low-dimensional confounder. In our model, there are $L$ observed contexts and $K$ arms of the bandit. The observed context influences the reward obtained through a latent confounder var…

This paper studies the Best-of-K Bandit game: At each time the player chooses a subset S among all N-choose-K possible options and observes reward max(X(i) : i in S) where X is a random vector drawn from a joint distribution. The objective is to identify the subset that achieves the highest expected reward with high pr…

Two novel methods identify influential features in CMABs for better reward distribution.

A new method reduces feature screening cost from $O(np)$ to $O(\sqrt{n}p)$.

Data-driven method for error estimation without needing class complexity.

New algorithm reduces reinforcement learning regret for linear MDPs with unknown transitions.

Algorithm optimizes bandit decisions with changing action sets using Gaussian processes.