Non-stationary Bandits with Knapsacks

Authors: Shang Liu, Jiashuo Jiang, Xiaocheng Li

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Numerical experiments compare the performance of our algorithm with existing Bw K algorithms and are presented in Appendix A.
Researcher Affiliation Academia Imperial College Business School, Imperial College London NYU Stern School of Business s.liu21@imperial.ac.uk, jj2398@stern.nyu.edu, xiaocheng.li@imperial.ac.uk
Pseudocode Yes Algorithm 1 Sliding-Window UCB Algorithm for Bw K
Open Source Code No The paper mentions numerical experiments and an algorithm but does not provide any explicit statements about open-source code availability or links to repositories.
Open Datasets No The paper refers to "Numerical experiments" in Appendix A, but does not specify any publicly available datasets, provide links, or formal citations for them in the main text.
Dataset Splits No The paper mentions "Numerical experiments" but does not provide specific details on training, validation, or test dataset splits.
Hardware Specification No The paper does not provide any specific details about the hardware used for the experiments.
Software Dependencies No The paper does not mention any specific software dependencies with version numbers.
Experiment Setup No The paper describes Algorithm 1 but does not provide specific details about experimental setup, such as hyperparameters or system-level training settings.