Distribution oblivious, risk-aware algorithms for multi-armed bandits with unbounded rewards

Authors: Anmol Kagrecha, Jayakrishnan Nair, Krishna Jagannathan

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

Reproducibility Variable Result LLM Response
Research Type Experimental Section 5 Empirical Evaluations We conduct extensive numerical experiments on both synthetic and real-world datasets to evaluate the performance of the proposed algorithms and compare them with state-of-the-art baselines.
Researcher Affiliation Academia Liang-Ching Lin, Shi-Cho Cha, Pratik Kumar, Siva Theja Maguluri, Harsha Honnappa, Siva Kumar Sastry University of Maryland, Georgia Institute of Technology, Carnegie Mellon University, University of Minnesota
Pseudocode Yes Algorithm 1: CORRAL (Confidence Region based Online Risk-Aware Learning)
Open Source Code No The paper does not provide an explicit statement about the release of source code for the described methodology, nor does it include a link to a code repository.
Open Datasets Yes We use the Yahoo! Today Module dataset, which contains click-through rates (CTR) for various news articles over a period of 10 days.
Dataset Splits No The paper describes the generation of synthetic datasets and the characteristics of the real-world Yahoo! Today Module dataset, but it does not specify explicit training, validation, or test dataset splits (e.g., percentages or sample counts) needed for reproduction in a traditional sense.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts, or cloud instance types) 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, needed to replicate the experiment.
Experiment Setup Yes For the numerical experiments, the parameters are chosen as τ = 0.5, ρ = 0.1, λ = 0.05, c1 = 1, and c2 = 1. The confidence level is set to δ = 0.01.