Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits
Authors: Yogev Bar-On, Yishay Mansour
NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We derive regret minimization algorithms that guarantee for each agent v an individual expected regret of e O r 1 + K |N (v)| T , Our main contribution is an individual expected regret bound, which holds for each agent v, of order s 1 + K |N (v)|, We will now provide an overview for the analysis of our algorithms. We remind that all proofs are differed to the supplementary material. |
| Researcher Affiliation | Collaboration | Yogev Bar-On Tel Aviv University, Israel baronyogev@gmail.com Yishay Mansour Tel Aviv University, Israel and Google Research, Israel mansour.yishay@gmail.com |
| Pseudocode | Yes | Algorithm 1 Center-based cooperative MAB v is a center agent, Algorithm 2 Center-based cooperative MAB v is a non-center agent, Algorithm 3 Centers-to-Components, Algorithm 4 Compute-Centers-Informed, Algorithm 5 Compute-Centers-Uninformed. |
| Open Source Code | No | The paper does not contain any statement about making its source code publicly available, nor does it provide a link to a code repository. |
| Open Datasets | No | This is a theoretical paper that does not use or reference any datasets for training or evaluation. |
| Dataset Splits | No | This is a theoretical paper and does not describe any dataset splits (train, validation, test) as it does not involve empirical evaluation. |
| Hardware Specification | No | The paper does not provide any specific hardware details used for running experiments, as it is a theoretical work. |
| Software Dependencies | No | The paper does not specify any software dependencies with version numbers, as it focuses on theoretical algorithms and their analysis. |
| Experiment Setup | No | This is a theoretical paper and does not provide details about an experimental setup, such as hyperparameters or training configurations, as it does not involve empirical experiments. |