Bandits with Concave Aggregated Reward

Authors: Yingqi Yu, Sijia Zhang, Shaoang Li, Lan Zhang, Wei Xie, Xiang-Yang Li

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive simulations demonstrate that our algorithms achieve better results than the most advanced bandit algorithms.
Researcher Affiliation Academia University of Science and Technology of China, Hefei, China Institute of Artificial Intelligence, Hefei Comprehensive National Science Center
Pseudocode Yes Algorithm 1: SW-BCAR
Open Source Code No The paper does not contain an explicit statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets No The paper describes generating data from 'truncated normal distributions' for simulations but does not refer to a publicly available dataset with a specific name, link, or formal citation.
Dataset Splits No The paper describes simulation parameters and performance evaluation over different settings, but it does not specify training, validation, and test dataset splits in the context of data partitioning for reproduction.
Hardware Specification No The paper discusses simulations and evaluations but does not specify any hardware details like GPU/CPU models or memory used for running the experiments.
Software Dependencies No The paper refers to benchmark algorithms but does not provide specific software names with version numbers for implementation dependencies (e.g., Python, PyTorch).
Experiment Setup Yes In the experiments, variables other than specified separately were fixed as follows: 1) the round number T = 20000; the arm number K = 2; 2) the optimal arm s mean value µ = 0.8; the suboptimal arms mean values µ(a) = 0.4; 3) the aggregated reward function f(x) = 1 + x 1; 4) the parameter for the value range σ = 2.