Certainty Equivalence is Efficient for Linear Quadratic Control

• DOI: 10.48550/arxiv.1902.07826
• Publication Date: 2019-01-01
• Authors: Mania, Horia; Tu, Stephen; Recht, Benjamin
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; 0209 industrial biotechnology; Statistics - Machine Learning; Optimization and Control (math.OC); FOS: Mathematics; Machine Learning (stat.ML); 02 engineering and technology; Mathematics - Optimization and Control; Machine Learning (cs.LG)

In the current version we extended our analysis to the case of partially observable systems, i.e. we provided a suboptimality analysis for the Linear Quadratic Gaussian (LQG) setting<br/>We study the performance of the certainty equivalent controller on Linear Quadratic (LQ) control problems with unknown transition dynamics. 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. To the best of our knowledge, our result is the first sub-optimality guarantee in the partially observed Linear Quadratic Gaussian (LQG) setting. Furthermore, in the fully observed Linear Quadratic Regulator (LQR), our result improves upon recent work by Dean et al. (2017), who present an algorithm achieving a sub-optimality gap linear in the parameter error. A key part of our analysis relies on perturbation bounds for discrete Riccati equations. We provide two new perturbation bounds, one that expands on an existing result from Konstantinov et al. (1993), and another based on a new elementary proof strategy.<br/>