A New Algorithm for the LQR Problem with Partially Unknown Dynamics

05/28/2021
by   Agnese Pacifico, et al.
0

We consider an LQR optimal control problem with partially unknown dynamics. We propose a new model-based online algorithm to obtain an approximation of the dynamics and the control at the same time during a single simulation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/12/2012

Reinforcement Learning with Partially Known World Dynamics

Reinforcement learning would enjoy better success on real-world problems...
research
03/18/2022

Time-Optimal Online Replanning for Agile Quadrotor Flight

In this paper, we tackle the problem of flying a quadrotor using time-op...
research
11/17/2019

Optimal Control of a Differentially Flat 2D Spring-Loaded Inverted Pendulum Model

This paper considers the optimal control problem of an extended spring-l...
research
09/18/2016

Learning Personalized Optimal Control for Repeatedly Operated Systems

We consider the problem of online learning of optimal control for repeat...
research
10/23/2022

LQGNet: Hybrid Model-Based and Data-Driven Linear Quadratic Stochastic Control

Stochastic control deals with finding an optimal control signal for a dy...
research
01/06/2019

Optimal Network Control in Partially-Controllable Networks

The effectiveness of many optimal network control algorithms (e.g., Back...
research
07/16/2021

Robust Online Control with Model Misspecification

We study online control of an unknown nonlinear dynamical system that is...

Please sign up or login with your details

Forgot password? Click here to reset