-
Yahoo! Dataset
A real-world dataset collected from the Yahoo! Front Page Today Module, containing a large-scale collection of anonymized user click logs -
Synthetic Environment
A synthetic environment where the reward means originate from a Bernoulli distribution with different parameters and several local change-points -
Multi-user Multi-armed Bandits for Uncoordinated Spectrum Access
The proposed algorithm consists of an estimation phase and an allocation phase. It is shown that if every user adopts the algorithm, the system wide regret is constant with time... -
Approximation to Bayes Risk in Repeated Play
A classic algorithm for approximating Bayes risk in repeated play. -
Skyline Identification in Multi-Armed Bandits
The dataset is used to test the ε-skyline identification problem, a variant of the classical PAC multi-armed bandit problem. -
Maximizing and Satisficing in Multi-armed Bandits with Graph Information
The dataset used in the paper is a graph-based multi-armed bandit problem with similarity graph information. -
Learning in Restless Multi-Armed Bandits via Adaptive Arm Sequencing Rules
Learning in restless multi-armed bandits via Adaptive Arm Sequencing Rules -
X-armed bandits
X-armed bandits is a framework for multi-armed bandit problems that uses a linear programming approach. -
Multi-Armed Bandits with Abstention
The authors introduce a novel extension of the canonical multi-armed bandit problem that incorporates an additional strategic element: abstention. -
Zero-Inflated Bandits
The Zero-Inflated Bandits problem is a variant of the multi-armed bandit problem where the reward is modeled as a zero-inflated distribution. The authors propose two algorithms,... -
EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits
The authors used four real-world datasets: MNIST, Yelp, MovieLens, and Disin.
