Queueing Matching Bandits with Preference Feedback

Authors: Jung-hun Kim, Min-hwan Oh

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

Reproducibility Variable Result LLM Response
Research Type Experimental Lastly, we provide experimental results to demonstrate the performance of our algorithms.
Researcher Affiliation Academia Jung-hun Kim Seoul National University Seoul, South Korea junghunkim@snu.ac.kr Min-hwan Oh Seoul National University Seoul, South Korea minoh@snu.ac.kr
Pseudocode Yes Algorithm 1 UCB-Queueing Matching Bandit (UCB-QMB) [...] Algorithm 2 Thompson Sampling-Queueing Matching Bandit (TS-QMB)
Open Source Code Yes The source code is available at https://github.com/junghunkim7786/Queueing-Matching-Bandits-with-Preference-Feedback
Open Datasets Yes For the synthetic experiments, we consider N = 4, K = 2, L = 2, and d = 2. Each element in xn and θk is uniformly generated from [0, 1] and then normalized, and λn s are determined with ϵ = 0.1. [...] The source code is available at https://github.com/junghunkim7786/Queueing-Matching-Bandits-with-Preference-Feedback
Dataset Splits No The paper describes parameters for generating synthetic data but does not explicitly mention any training, validation, or testing splits of this generated data. The experiments are conducted over a 'Time step t'.
Hardware Specification No The paper does not provide specific details about the hardware used for experiments. The NeurIPS checklist confirms this, stating, 'The conducted experiments do not require significant computing power.'
Software Dependencies No The paper does not list specific versions for any software dependencies (e.g., Python, PyTorch, TensorFlow, or any libraries/solvers).
Experiment Setup Yes For the synthetic experiments, we consider N = 4, K = 2, L = 2, and d = 2. Each element in xn and θk is uniformly generated from [0, 1] and then normalized, and λn s are determined with ϵ = 0.1.