Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
On the Complexity of Best-Arm Identification in Multi-Armed Bandit Models
Authors: Emilie Kaufmann, Olivier Cappé, Aurélien Garivier
JMLR 2016 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Section 6 contains numerical experiments that illustrate the performance of matching algorithms for Gaussian and Bernoulli two-armed bandits, comparing the fixed-confidence and fixed-budget settings. |
| Researcher Affiliation | Academia | Emilie Kaufmann EMAIL LTCI, CNRS, T el ecom Paris Tech 46, rue Barrault, 75013 Paris Olivier Capp e EMAIL LTCI, CNRS, T el ecom Paris Tech 46, rue Barrault, 75013 Paris Aur elien Garivier EMAIL Institut de Math ematiques de Toulouse ; UMR5219 Universit e de Toulouse ; CNRS UPS IMT, F-31062 Toulouse Cedex 9 |
| Pseudocode | Yes | Algorithm 1 α-Elimination Algorithm 2 Sequential Generalized Likelihood Ratio Test (SGLRT) |
| Open Source Code | No | The paper does not contain an explicit statement about the release of source code, nor does it provide a direct link to a code repository. |
| Open Datasets | No | The paper focuses on theoretical bandit models (e.g., Gaussian, Bernoulli bandit models) and describes numerical experiments based on these models. It does not refer to or use any specific publicly available datasets. |
| Dataset Splits | No | The paper does not use specific publicly available datasets, and therefore does not provide any dataset split information. |
| Hardware Specification | No | The paper does not explicitly mention any specific hardware (e.g., GPU, CPU models, memory specifications) used for running the numerical experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies or version numbers for any libraries, frameworks, or programming languages used in the implementation of the algorithms or experiments. |
| Experiment Setup | Yes | In the fixed-confidence setting, we report results for elimination algorithms of the form (14) for three different exploration rates β(t, δ). The exploration rate we consider are: the provably-PAC rate of Robbins algorithm log(t/δ) (large blue symbols), the conjectured optimal exploration rate log((log(t) + 1)/δ), almost provably δ-PAC according to Theorem 8 (bold green symbols), and the rate log(1/δ), which would be appropriate if we were to perform the stopping test only at a single pre-specified time (orange symbols). |