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 Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Stochastic Gradient Succeeds for Bandits
Authors: Jincheng Mei, Zixin Zhong, Bo Dai, Alekh Agarwal, Csaba Szepesvari, Dale Schuurmans
ICML 2023 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Section 7 presents a simulation study to verify the theoretical findings |
| Researcher Affiliation | Collaboration | 1Google Research, Brain Team 2University of Alberta 3Georgia Tech 4Google Research. |
| Pseudocode | Yes | Algorithm 1 Gradient bandit algorithm (without baselines) |
| Open Source Code | No | The paper does not provide any statement about releasing source code or a link to a code repository for the methodology described. |
| Open Datasets | No | The mean reward r is random generated in (0, 1)K. For each sampled action at πθt( ), the observed reward is generated as Rt(at) = r(at)+ Zt, where Zt N(0, 1) is Gaussian noise. |
| Dataset Splits | No | The paper does not provide specific dataset split information (percentages, sample counts, citations to predefined splits, or detailed splitting methodology). |
| Hardware Specification | No | The paper describes simulation experiments but does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running them. |
| Software Dependencies | No | The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment. |
| Experiment Setup | Yes | The learning rate is η = 0.01. We use adversarial initialization, such that πθ1(a ) < 1/K. |