Certainty Equivalence is Efficient for Linear Quadratic Control

Authors: Horia Mania, Stephen Tu, Benjamin Recht

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We show that for both the fully and partially observed settings, the sub-optimality gap between the cost incurred by playing the certainty equivalent controller on the true system and the cost incurred by using the optimal LQ controller enjoys a fast statistical rate, scaling as the square of the parameter error.In this work, we show that for the standard baseline of controlling an unknown linear dynamical system with a quadratic objective function known as Linear Quadratic (LQ) control, certainty equivalent control synthesis achieves better cost than prior methods that account for model uncertainty. Our results hold for both the fully observed Linear Quadratic Regulator (LQR) and the partially observed Linear Quadratic Gaussian (LQG) setting.
Researcher Affiliation Academia Horia Mania University of California, Berkeley hmania@berkeley.edu Stephen Tu University of California, Berkeley stephentu@berkeley.edu Benjamin Recht University of California, Berkeley brecht@berkeley.edu
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper is theoretical and does not mention providing access to any open-source code for the described methodology.
Open Datasets No This paper is theoretical and does not use or refer to any datasets for training or evaluation.
Dataset Splits No This paper is theoretical and does not discuss dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any specific hardware used for experiments.
Software Dependencies No The paper is theoretical and does not list any specific software dependencies or their version numbers.
Experiment Setup No The paper is theoretical and does not include details on experimental setup, hyperparameters, or training configurations.