Linear Stochastic Bandits Under Safety Constraints

Authors: Sanae Amani, Mahnoosh Alizadeh, Christos Thrampoulidis

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our simulation results in Appendix F emphasize the critical role of a sufficiently long pure exploration phase by Safe-LUCB as suggested by Lemma 2. Specifically, Figure 1b depicts an instance where no exploration leads to significantly worse order of regret.
Researcher Affiliation Academia Sanae Amani University of California, Santa Barbara samanigeshnigani@ucsb.edu Mahnoosh Alizadeh University of California, Santa Barbara alizadeh@ucsb.edu Christos Thrampoulidis University of California, Santa Barbara cthrampo@ucsb.edu
Pseudocode Yes Algorithm 1 Safe-LUCB
Open Source Code No The paper does not contain any explicit statements about providing open-source code or links to a code repository for the described methodology.
Open Datasets No The paper conducts simulations using a 'simplified setting of K-armed linear bandits' but does not specify or provide access information for any publicly available or open dataset.
Dataset Splits No The paper discusses simulation results but does not provide specific details on dataset splits (e.g., train/validation/test percentages or sample counts) for reproducibility.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, or memory) used for running its experiments or simulations.
Software Dependencies No The paper does not list any specific software dependencies, libraries, or their version numbers used in the implementation or simulations.
Experiment Setup No The paper mentions 'The details on the parameters of the simulations are deferred to Appendix F' but does not provide specific experimental setup details (e.g., hyperparameter values, training configurations) within the main text.