Gamification of Pure Exploration for Linear Bandits

Authors: Rémy Degenne, Pierre Menard, Xuedong Shang, Michal Valko

ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 5. Experiments Besides our algorithms, we implement the following algorithms... Fig. 1 shows the empirical stopping time of each algorithms averaged over 100 runs... Fig. 2. Sample complexity over random unit sphere vectors...
Researcher Affiliation Collaboration 1INRIA DIENS PSL Research University, Paris, France 2INRIA 3INRIA Universit e de Lille 4Deep Mind Paris.
Pseudocode Yes Algorithm 1 Lin Game Algorithm 2 Lin Game-C
Open Source Code No The paper does not provide concrete access to source code for the methodology described, nor does it include a specific repository link or an explicit code release statement.
Open Datasets No The paper evaluates on 'synthetic problem instances' and 'random unit sphere vectors', which are generated for the experiments. It does not provide access information (link, DOI, repository, or citation) for a publicly available or open dataset.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) for training, validation, or testing.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as library or solver names with version numbers, that would be needed to replicate the experiment.
Experiment Setup Yes We set d = 2, α = π/6. Fig. 1 shows the empirical stopping time of each algorithms averaged over 100 runs, with a confidence level δ = 0.1, 0.01, 0.0001 from left to right... We set d = 6, 8, 10, 12 respectively, and always keep a same δ = 0.01.