Online Learning in Stackelberg Games with an Omniscient Follower

Authors: Geng Zhao, Banghua Zhu, Jiantao Jiao, Michael Jordan

ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We study the problem of online learning in a two-player decentralized cooperative Stackelberg game. We analyze the sample complexity of regret minimization in this repeated Stackelberg game. We show that depending on the reward structure, the existence of the omniscient follower may change the sample complexity drastically, from constant to exponential, even for linear cooperative Stackelberg games. This poses unique challenges for the learning process of the leader and the subsequent regret analysis.
Researcher Affiliation Academia 1Department of EECS, University of California, Berkeley, USA.
Pseudocode Yes Algorithm 1 UCB with side information from expert
Open Source Code No The paper does not provide any specific links or statements about the availability of open-source code for the described methodology.
Open Datasets No The paper focuses on theoretical analysis and does not mention the use of specific datasets for training.
Dataset Splits No The paper focuses on theoretical analysis and does not discuss training, validation, or test dataset splits.
Hardware Specification No The paper is theoretical and does not mention any specific hardware used for experiments.
Software Dependencies No The paper is theoretical and does not mention specific software dependencies with version numbers.
Experiment Setup No The paper focuses on theoretical analysis and does not include specific experimental setup details, hyperparameters, or training configurations.