Robust Control in the Worst Case Using Continuous Time Reinforcement Learning

Reinforcement learning (RL) is an effective method to design robust control. Uncertainty in the worst case requires large state-action learning space. The continuous time RL can solve this computational problem. In this paper, we modify the classical continuous time RL. Compared with the actor-critic (AC) algorithm, our method is more simple and more robust under the worst-case uncertainty.