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].
Best Model Identification: A Rested Bandit Formulation
Authors: Leonardo Cella, Massimiliano Pontil, Claudio Gentile
ICML 2021 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In Appendix D we included simple preliminary experiments on synthetic data that help corroborate our theoretical ๏ฌndings. |
| Researcher Affiliation | Collaboration | 1Italian Institute of Technology, Genoa, Italy 2University College London, United Kingdom 3Google Research, New York, USA. |
| Pseudocode | Yes | Algorithm 1 Explore-Then-Commit (ETC) [...] Algorithm 2 REST-SURE |
| Open Source Code | No | The paper does not provide any explicit statement or link for open-source code for the methodology described. |
| Open Datasets | No | We use a synthetic dataset with K = 2 arms and a time horizon T = 1000... |
| Dataset Splits | No | The paper does not explicitly provide training/test/validation dataset splits. It mentions using synthetic data for preliminary experiments but no specific split information. |
| Hardware Specification | No | The paper does not explicitly describe the hardware used to run its experiments. |
| Software Dependencies | No | The paper does not provide specific version numbers for ancillary software dependencies. |
| Experiment Setup | No | The paper mentions parameters for the synthetic data setup (K=2, T=1000) in Appendix D, but does not provide specific experimental setup details such as hyperparameters or system-level training settings for the algorithms themselves in the main text. |