This manuscript surveys reinforcement learning from the perspective of
optimization and control with a focus on continuous control applications. It
surveys the general formulation, terminology, and typical experimental
implementations of reinforcement learning and reviews competing solution
paradigms. In order to compare the relative merits of various techniques, this
survey presents a case study of the Linear Quadratic Regulator (LQR) with
unknown dynamics, perhaps the simplest and best studied problem in optimal
control. The manuscript describes how merging techniques from learning theory
and control can provide non-asymptotic characterizations of LQR performance and
shows that these characterizations tend to match experimental behavior. In
turn, when revisiting more complex applications, many of the observed phenomena
in LQR persist. In particular, theory and experiment demonstrate the role and
importance of models and the cost of generality in reinforcement learning
algorithms. This survey concludes with a discussion of some of the challenges
in designing learning systems that safely and reliably interact with complex
and uncertain environments and how tools from reinforcement learning and
controls might be combined to approach these challenges.
Description
[1806.09460] A Tour of Reinforcement Learning: The View from Continuous Control
%0 Generic
%1 recht2018reinforcement
%A Recht, Benjamin
%D 2018
%K 2018 arxiv control optimization paper reinforcement-learning
%T A Tour of Reinforcement Learning: The View from Continuous Control
%U http://arxiv.org/abs/1806.09460
%X This manuscript surveys reinforcement learning from the perspective of
optimization and control with a focus on continuous control applications. It
surveys the general formulation, terminology, and typical experimental
implementations of reinforcement learning and reviews competing solution
paradigms. In order to compare the relative merits of various techniques, this
survey presents a case study of the Linear Quadratic Regulator (LQR) with
unknown dynamics, perhaps the simplest and best studied problem in optimal
control. The manuscript describes how merging techniques from learning theory
and control can provide non-asymptotic characterizations of LQR performance and
shows that these characterizations tend to match experimental behavior. In
turn, when revisiting more complex applications, many of the observed phenomena
in LQR persist. In particular, theory and experiment demonstrate the role and
importance of models and the cost of generality in reinforcement learning
algorithms. This survey concludes with a discussion of some of the challenges
in designing learning systems that safely and reliably interact with complex
and uncertain environments and how tools from reinforcement learning and
controls might be combined to approach these challenges.
@misc{recht2018reinforcement,
abstract = {This manuscript surveys reinforcement learning from the perspective of
optimization and control with a focus on continuous control applications. It
surveys the general formulation, terminology, and typical experimental
implementations of reinforcement learning and reviews competing solution
paradigms. In order to compare the relative merits of various techniques, this
survey presents a case study of the Linear Quadratic Regulator (LQR) with
unknown dynamics, perhaps the simplest and best studied problem in optimal
control. The manuscript describes how merging techniques from learning theory
and control can provide non-asymptotic characterizations of LQR performance and
shows that these characterizations tend to match experimental behavior. In
turn, when revisiting more complex applications, many of the observed phenomena
in LQR persist. In particular, theory and experiment demonstrate the role and
importance of models and the cost of generality in reinforcement learning
algorithms. This survey concludes with a discussion of some of the challenges
in designing learning systems that safely and reliably interact with complex
and uncertain environments and how tools from reinforcement learning and
controls might be combined to approach these challenges.},
added-at = {2018-07-25T17:29:44.000+0200},
author = {Recht, Benjamin},
biburl = {https://www.bibsonomy.org/bibtex/2b462da0d83aebc30f5f1675b51421f7e/analyst},
description = {[1806.09460] A Tour of Reinforcement Learning: The View from Continuous Control},
interhash = {b8c832ff62364a583dada7ed0566e49f},
intrahash = {b462da0d83aebc30f5f1675b51421f7e},
keywords = {2018 arxiv control optimization paper reinforcement-learning},
note = {cite arxiv:1806.09460},
timestamp = {2018-07-25T17:29:44.000+0200},
title = {A Tour of Reinforcement Learning: The View from Continuous Control},
url = {http://arxiv.org/abs/1806.09460},
year = 2018
}