… linear system. Extension of our result to control a nonlinear system will be considered in future…
Moreover, implementation of the propose approach to control of real-world systems and its …

… -based reinforcement learning theory to Linear Quadratic Reg… simple type of non-linear
function approximator. We describe … algorithms when applied to non-linear systems for which the …

… a Q-learning algorithm is proposed to solve the linear quadratic regulator problem of black
box linear systems. The … An integral reinforcement learning approach is used to develop the Q-…

… the system states and it is desirable to design output-feedback controllers. This paper develops
an online learning … controller for partially unknown CT linear systems. The proposed IRL-…

… We give an overview of recent exciting achievements of deep reinforcement learning (RL). …
We start with background of machine learning, deep learning and reinforcement learning. …

… A powerful reinforcement learning algorithm for these applications should have regret which
… of a noise driven system (ie, no control) whose dynamics are modeled by linear stochastic …

… based reinforcement learning (RL) in unknown stabilizable linear dynamical systems.
When … We propose an algorithm that certifies fast stabilization of the underlying system by …

… linear regresser, based on least-squares regression, whose analysis may be of interest to
the online learning … online linear regression and pose a new online learning framework that …

… In this section, the optimal control of CT linear systems is formulated. A discounted
performance function is used to make the proposed method applicable for both LQR and LQT …

… For linear systems which are the focus of this technical note, … for both DT systems [11]–[13]
and CT systems [14]–[16]. … RL techniques for both DT systems [17]–[21] and CT systems [22]. …