Reinforcement learning and feedback control: Using natural decision methods to design optimal adaptive controllers

FL Lewis, D Vrabie… - IEEE Control Systems …, 2012 - ieeexplore.ieee.org
… This article describes the use of principles of reinforcement learning to design feedback
and algorithms of reinforcement learning and their applications to feedback control of dynamical …

[图书][B] Reinforcement learning for optimal feedback control

R Kamalapurkar, P Walters, J Rosenfeld, W Dixon - 2018 - Springer
reinforcement learning-based solutions, where learning occurs through an actor–critic-based
reward system. Detailed attention to control-… literature on reinforcement learning. Moreover, …

Feedback control for cassie with deep reinforcement learning

Z Xie, G Berseth, P Clary, J Hurst… - 2018 IEEE/RSJ …, 2018 - ieeexplore.ieee.org
reinforcement learning, feedback control and how we transform a feedback control problem
into a reinforcement learning … to that of our learned feedback controller in a later section. A …

Reinforcement learning in feedback control: Challenges and benchmarks from technical process control

R Hafner, M Riedmiller - Machine learning, 2011 - Springer
… for the benchmarks we introduce for learning feedback control. Within the scope of this …
especially within the context of reinforcement learning for feedback control applications. It was …

A novel approach to feedback control with deep reinforcement learning

Y Wang, K Velswamy, B Huang - IFAC-PapersOnLine, 2018 - Elsevier
… (RL) algorithm is applied for feedback control application. We propose Proximal Actor-Critic,
a model-free reinforcement learning algorithm that can learn robust feedback control laws …

Reinforcement learning-based output feedback control of nonlinear systems with input constraints

P He, S Jagannathan - … on Systems, Man, and Cybernetics, Part …, 2005 - ieeexplore.ieee.org
… output feedback controller design is quite difficult and challenging. Several output feedback
controller … In this paper, an output feedback controller design using the adaptive critic neural …

Feedback controller parameterizations for reinforcement learning

JW Roberts, IR Manchester… - … Reinforcement Learning …, 2011 - ieeexplore.ieee.org
feedback control studied in this paper: Feedback Controller Transfer Function, State Feedback
… • Section IV A presentation of the REINFORCE method used for learning in this paper • …

Optimal and autonomous control using reinforcement learning: A survey

B Kiumarsi, KG Vamvoudakis… - … and learning systems, 2017 - ieeexplore.ieee.org
reinforcement learning (RL)-based feedback control solutions to optimal … control problems,
as well as graphical games, will be reviewed. RL methods learn the solution to optimal control

A reinforcement learning-empowered feedback control system for industrial internet of things

X Chen, J Hu, Z Chen, B Lin, N Xiong… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
reinforcement learning (RL)-empowered feedback control method for cooperative load balancing
(RFCLB). First, by integrating RL and machine learning … Next, through feedback control

Optimal output-feedback control of unknown continuous-time linear systems using off-policy reinforcement learning

H Modares, FL Lewis, ZP Jiang - IEEE Transactions on …, 2016 - ieeexplore.ieee.org
… In this section, a state-feedback model-free Off-policy RL algorithm is given to learn the
solution to the discounted optimal control problem formulated in Section II-A. This algorithm does …