Add to ORKGIn this paper, we study the statistical difficulty of learning to control linear systems. We focus on two standard benchmarks, the sample complexity of stabilization, and the regret of the online learning of the Linear Quadratic Regulator (LQR). Prior results state that the statistical difficulty for both benchmarks scales polynomially with the system state dimension up to system-theoretic quantities. However, this does not reveal the whole picture. By utilizing minimax lower bounds for both benchmarks, we prove that there exist non-trivial classes of systems for which learning complexity scales dramatically, i.e. exponentially, with the system dimension. This situation arises in the case of underactuated systems, i.e. systems with fewer in...
In this paper we show how some difficult linear algebra problems can be “approximately” solved usin...
As the systems we control become more complex, first-principle modeling becomes either impossible or...
When models are inaccurate, the performance of model-based control will degrade. For linear quadrati...
Reinforcement learning (RL) has demonstrated impressive performance in various domains such as video...
The field of linear control has seen broad application in fields as diverse as robotics, aviation,...
Despite the recent widespread success of machine learning, we still do not fully understand its fund...
Learning algorithms play an ever increasing role in modern engineering solutions. However, despite m...
We consider the problem of online adaptive control of the linear quadratic regulator, where the true...
Learning controllers from data for stabilizing dynamical systems typically follows a two step proces...
It has recently become clear that many control problems are too difficult to admit analytic solution...
A fundamental concept in control theory is that of controllability, where any system state can be re...
This paper addresses the optimal control problem known as the linear quadratic regulator in the case...
In this work, we study model-based reinforcement learning (RL) in unknown stabilizable linear dynami...
This paper considers the Linear Quadratic Regulator problem for linear systems with unknown dynamics...
he topic of the present article is the use of randomized algo- T rithms to solve some problems in co...
In this paper we show how some difficult linear algebra problems can be “approximately” solved usin...
As the systems we control become more complex, first-principle modeling becomes either impossible or...
When models are inaccurate, the performance of model-based control will degrade. For linear quadrati...
Reinforcement learning (RL) has demonstrated impressive performance in various domains such as video...
The field of linear control has seen broad application in fields as diverse as robotics, aviation,...
Despite the recent widespread success of machine learning, we still do not fully understand its fund...
Learning algorithms play an ever increasing role in modern engineering solutions. However, despite m...
We consider the problem of online adaptive control of the linear quadratic regulator, where the true...
Learning controllers from data for stabilizing dynamical systems typically follows a two step proces...
It has recently become clear that many control problems are too difficult to admit analytic solution...
A fundamental concept in control theory is that of controllability, where any system state can be re...
This paper addresses the optimal control problem known as the linear quadratic regulator in the case...
In this work, we study model-based reinforcement learning (RL) in unknown stabilizable linear dynami...
This paper considers the Linear Quadratic Regulator problem for linear systems with unknown dynamics...
he topic of the present article is the use of randomized algo- T rithms to solve some problems in co...
In this paper we show how some difficult linear algebra problems can be “approximately” solved usin...
As the systems we control become more complex, first-principle modeling becomes either impossible or...
When models are inaccurate, the performance of model-based control will degrade. For linear quadrati...