Policy Iteration for Linear Quadratic Games With Stochastic Parameters.

Robustness is a key challenge in the integration of learning and control. In machine learning and robotics, two common approaches to promote robustness are adversarial training and domain randomization. Both of these approaches have analogs in control theory: adversarial training relates to H∞ control and dynamic game theory, while domain randomization relates to theory for systems with stochastic...