Handling Heterogeneous Curvatures in Bandit LQR Control

Authors: Yu-Hu Yan, Jing Wang, Peng Zhao

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

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper presents work whose goal is to advance the field of Machine Learning. There are many potential societal consequences of our work, none which we feel must be specifically highlighted here. Finally, we achieve interpolated guarantees that can not only recover existing bounds for convex and quadratic costs but also attain new implications for cases of corrupted and decaying quadraticity.
Researcher Affiliation Academia 1National Key Laboratory for Novel Software Technology, Nanjing University, China 2School of Artificial Intelligence, Nanjing University, China. Correspondence to: Peng Zhao <zhaop@lamda.nju.edu.cn>.
Pseudocode Yes Algorithm 1 Subroutine of Luo et al. (2022) Algorithm 2 Heterogeneous Bandit LQR Control
Open Source Code No The paper does not provide any explicit statements about releasing source code for its methodology or links to code repositories.
Open Datasets No The paper focuses on theoretical analysis and does not involve experimental training on datasets; therefore, no information about public datasets is provided.
Dataset Splits No The paper is theoretical and does not involve experimental validation on datasets; therefore, no information about training/test/validation splits is provided.
Hardware Specification No The paper is theoretical and does not describe any experiments that would require specific hardware; therefore, no hardware specifications are mentioned.
Software Dependencies No The paper focuses on theoretical contributions and does not describe any implemented software with specific version numbers for replication.
Experiment Setup No The paper is theoretical and does not describe practical experiments with specific setup details, hyperparameters, or training configurations.