Gradient-based methods have been widely used for system design and optimization in
diverse application domains. Recently, there has been a renewed interest in studying …

Experience replay is central to off-policy algorithms in deep reinforcement learning (RL), but
there remain significant gaps in our understanding. We therefore present a systematic and …

Policy optimization (PO) is a key ingredient for modern reinforcement learning (RL). For
control design, certain constraints are usually enforced on the policies to optimize …

The trajectory tracking plays a vital role in unmanned driving technology. Although
traditional control schemes may yield satisfactory outcomes in dealing with simple linear …

The linear quadratic regulator (LQR) problem has reemerged as an important theoretical
benchmark for reinforcement learning-based control of complex dynamical systems with …

We explore reinforcement learning methods for finding the optimal policy in the linear
quadratic regulator (LQR) problem. In particular we consider the convergence of policy …

We study model-free learning methods for the output-feedback Linear Quadratic (LQ) control
problem in finite-horizon subject to subspace constraints on the control policy. Subspace …

Reinforcement learning (RL) algorithms can fail to generalize due to the gap between the
simulation and the real world. One standard remedy is to use robust adversarial RL (RARL) …

The applications of direct policy search in reinforcement learning and continuous control
have received increasing attention. In this work, we present novel theoretical results on the …

We study a model-free federated linear quadratic regulator (LQR) problem where M agents
with unknown, distinct yet similar dynamics collaboratively learn an optimal policy to …