Learning in Online Principal-Agent Interactions: The Power of Menus

Authors: Minbiao Han, Michael Albert, Haifeng Xu

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We provide a thorough investigation of several online principal-agent problem settings and characterize their sample complexities, accompanied by the corresponding algorithms we have developed. and We propose the following algorithm 1 to learn the agent s true type 2 in log | | rounds.
Researcher Affiliation Academia 1Department of Computer Science, The University of Chicago 2Darden Business School, University of Virginia
Pseudocode Yes Algorithm 1: LEARNING-VIA-MENU and Algorithm 2: LEARNING-VIA-SINGLE-STRATEGY
Open Source Code No The paper does not provide concrete access to source code (specific repository link, explicit code release statement, or code in supplementary materials) for the methodology described.
Open Datasets No The paper is theoretical and does not involve empirical experiments with datasets that would require providing access information for training data.
Dataset Splits No The paper is theoretical and does not involve empirical experiments with datasets that would require providing specific dataset split information for validation.
Hardware Specification No The paper is theoretical and does not mention any specific hardware used for running experiments.
Software Dependencies No The paper is theoretical and does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate experiments.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with specific hyperparameter values or training configurations.