Results 111 to 120 of about 12,042 (216)

Regret-Optimal LQR Control [PDF]

, 2023
We consider the infinite-horizon LQR control problem. Motivated by competitive analysis in online learning, as a criterion for controller design we introduce the dynamic regret, defined as the difference between the LQR cost of a causal controller (that ...
Lale, Sahin, Hassibi, Babak, Sabag, Oron, Goel, Gautam   +3 more
core  

LQR and Fuzzy-PID Control Design on Double Inverted Pendulum

Cauchy: Jurnal Matematika Murni dan Aplikasi
Double inverted pendulum is a non-linear and unstable system. Double inverted pendulum can be stabilized in the upright position by providing control to the system.
Erlyana Trie Damayanti, Mardlijah Mardlijah, Ridho Nur Rohman Wijaya   +2 more
doaj   +1 more source

Stochastic LQR Design With Disturbance Preview

CoRR
This paper considers the discrete-time, stochastic LQR problem with $p$ steps of disturbance preview information where $p$ is finite. We first derive the solution for this problem on a finite horizon with linear, time-varying dynamics and time-varying costs.
Jietian Liu, Laurent Lessard, Peter J. Seiler   +2 more
openaire   +3 more sources

Policy Evaluation in Distributional LQR [PDF]

, 2023
Distributional reinforcement learning (DRL) enhances the understanding of the effects of the randomness in the environment by letting agents learn the distribution of a random return, rather than its expected value as in standard RL.
Johansson, Karl H., Abate, Alessandro, Zavlanos, Michael M., Gao, Yulong, Wang, Siyi, Wang, Zifan   +5 more
core  

Control synthesis in the case of cost index with receding horizon [PDF]

INCAS Bulletin
A modified quadratic cost problem for linear systems utilizes receding horizon control (moving terminal constraints) to achieve asymptotic stability and effective feedback stabilization.
Ioan URSU, Adrian TOADER, Daniela ENCIU, Mihaela DAVIDESCU, Cristiana JIDOVU   +4 more
doaj   +1 more source

Policy Gradient Bounds in Multitask LQR

IEEE Control Systems Letters
We analyze the performance of policy gradient in multitask linear quadratic regulation (LQR), where the system and cost parameters differ across tasks. The main goal of multitask LQR is to find a controller with satisfactory performance on every task.
Charis J. Stamouli, Leonardo F. Toso, Anastasios Tsiamis, George J. Pappas, James Anderson 0001   +4 more
openaire   +2 more sources

Quadrocopter control by LQR algorithm

, 2019
İnsansız hava araçları kullanımının artmasıyla birlikte bu araçların kontrolü günümüzde giderek önem kazanmıştır. Bu araç çeşitlerinden birisi olan üç serbestlik dereceli dört motorlu kuadkopter sisteminin (3 DOF Hover) kontrolü için çeşitli yöntemler ...
İçen, Muhammed
core   +1 more source

Linear quadratic regulator (LQR) controller design for DC Servo motor [PDF]

, 2013
This project is focused mainly on designing and implementing Linear Quadratic Regulator (LQR) controller and PID controller for a Dc servo motor.
Haron, Hartini Sharninayati
core  

Multi-Objective LQR with Linear Scalarization [PDF]

The framework of decision-making, modeled as a Markov Decision Process (MDP), typically assumes a single objective. However, practical scenarios often involve tradeoffs between multiple objectives. We address this in the Linear Quadratic Regulator (LQR),
Shah, Devavrat, Sinclair, Sean R., Jadbabaie, Ali   +2 more
core   +2 more sources

Regularization for Covariance Parameterization of Direct Data-Driven LQR Control

As the benchmark of data-driven control methods, the linear quadratic regulator (LQR) problem has gained significant attention. A growing trend is direct LQR design, which finds the optimal LQR gain directly from raw data and bypassing system ...
Chiuso, Alessandro, Dörfler, Florian, Zhao, Feiran   +2 more
core   +1 more source