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 …

Model-free reinforcement learning attempts to find an optimal control action for an unknown
dynamical system by directly searching over the parameter space of controllers. The …

For the control of connected and autonomous vehicles (CAVs), most existing methods focus
on model-based strategies. They require explicit knowledge of car-following dynamics of …

The linear quadratic regulator is the fundamental problem of optimal control. Its state
feedback version was set and solved in the early 1960s. However, the static output feedback …

This paper studies a class of partially observed Linear Quadratic Gaussian (LQG) problems
with unknown dynamics. We establish an end-to-end sample complexity bound on learning …

The convergence of policy gradient algorithms hinges on the optimization landscape of the
underlying optimal control problem. Theoretical insights into these algorithms can often be …

Direct policy search serves as one of the workhorses in modern reinforcement learning (RL),
and its applications in continuous control tasks have recently attracted increasing attention …

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) …

We develop the first end-to-end sample complexity of model-free policy gradient (PG)
methods in discrete-time infinite-horizon Kalman filtering. Specifically, we introduce the …

While the techniques in optimal control theory are often model-based, the policy optimization
(PO) approach directly optimizes the performance metric of interest. Even though it has been …