Incentivizing Combinatorial Bandit Exploration

Authors: Xinyan Hu, Dung Ngo, Aleksandrs Slivkins, Steven Z. Wu

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We prove that Thompson Sampling, when applied to combinatorial semi-bandits, is incentive-compatible when initialized with a sufficient number of samples of each arm (where this number is determined in advance by the Bayesian prior). Moreover, we design incentive-compatible algorithms for collecting the initial samples.
Researcher Affiliation Collaboration 1University of California, Berkeley. Email: xinyanhu@berkeley.edu 2University of Minnesota. Email: ngo00054@umn.edu 3Microsoft Research NYC. Email: slivkins@microsoft.com 4Carnegie Mellon University. Email: zstevenwu@cmu.edu
Pseudocode No The paper describes algorithms and their properties (e.g., "We present two such algorithms..."), but it does not include formal pseudocode blocks or algorithm listings.
Open Source Code No The paper does not contain any statement about releasing source code for the described methodology, nor does it provide links to a code repository.
Open Datasets No The paper is theoretical and does not involve empirical studies with datasets for training, validation, or testing.
Dataset Splits No The paper is theoretical and does not involve empirical studies with datasets for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe experiments that would require hardware specifications.
Software Dependencies No The paper is theoretical and does not specify software dependencies with version numbers for experimental reproducibility.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with hyperparameters or system-level training settings.