activity
20162026
most citedNon-Asymptotic Analysis of Robust Control from Coarse-Grained Identification

54 citations · 217 across the 13 of their papers we have counts for

collaborators
Showing 2018Show all

6 papers · 1 filter

cs.LG2018

The Gap Between Model-Based and Model-Free Methods on the Linear Quadratic Regulator: An Asymptotic Viewpoint

Stephen Tu, Benjamin Recht

The effectiveness of model-based versus model-free methods is a long-standing question in reinforcement learning (RL). Motivated by recent empirical success of RL on continuous con…

math.OC2018

Minimax Lower Bounds for -Norm Estimation

Stephen Tu, Ross Boczar, Benjamin Recht

The problem of estimating the -norm of an LTI system from noisy input/output measurements has attracted recent attention as an alternative to parameter identifi…

math.OC2018

Safely Learning to Control the Constrained Linear Quadratic Regulator

Sarah Dean, Stephen Tu, Nikolai Matni +1

We study the constrained linear quadratic regulator with unknown dynamics, addressing the tension between safety and exploration in data-driven control techniques. We present a fra…

cs.LG2018

Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator

Sarah Dean, Horia Mania, Nikolai Matni +2

We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs. Leveraging recent developments in the…

cs.RO2018

Learning Contracting Vector Fields For Stable Imitation Learning

Vikas Sindhwani, Stephen Tu, Mohi Khansari

We propose a new non-parametric framework for learning incrementally stable dynamical systems x' = f(x) from a set of sampled trajectories. We construct a rich family of smooth vec…

cs.LG2018

Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification

Max Simchowitz, Horia Mania, Stephen Tu +2

We prove that the ordinary least-squares (OLS) estimator attains nearly minimax optimal performance for the identification of linear dynamical systems from a single observed trajec…