Optimal Dynamic Regret in LQR Control

Authors: Dheeraj Baby, Yu-Xiang Wang

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

Reproducibility Variable Result LLM Response
Research Type Theoretical Paper of theoretical nature.
Researcher Affiliation Academia Dheeraj Baby Department of Computer Science UC Santa Barbara dheeraj@ucsb.edu Yu-Xiang Wang Department of Computer Science UC Santa Barbara yuxiangw@cs.ucsb.edu
Pseudocode Yes Figure 1: Pro DR.control: An algorithm for non-stationary and proper linear regression. Figure 2: Pro DR.control.delayed: An instance of delayed to non-delayed reduction from Joulani et al. [2013]
Open Source Code No Paper of theoretical nature.
Open Datasets No The paper is theoretical and does not involve empirical studies with datasets. The ethics checklist states: '[N/A] Paper of theoretical nature.' for questions related to experiments and data.
Dataset Splits No The paper is theoretical and does not involve empirical studies with datasets. The ethics checklist states: '[N/A] Paper of theoretical nature.' for questions related to experiments and data.
Hardware Specification No The paper is theoretical and does not describe any experiments that would require specific hardware. The ethics checklist states: '[N/A] Paper of theoretical nature.' for questions related to experiments.
Software Dependencies No The paper is theoretical and does not describe any experiments that would require specific software dependencies with version numbers. The ethics checklist states: '[N/A] Paper of theoretical nature.' for questions related to experiments.
Experiment Setup No The paper is theoretical and does not describe any experiments with specific hyperparameters or training settings. The ethics checklist states: '[N/A] Paper of theoretical nature.' for questions related to experiments.