Linear dynamical systems are a continuous subclass of reinforcement learning models that are widely used in robotics, finance, engineering, and meteorology. Classical control, since the works of Kalman, has focused on dynamics with Gaussian i.i.d. noise, quadratic loss functions and, in terms of provably efficient algorithms, known systems and observed state.
In this talk we'll discuss how to apply new machine learning methods to control which relax all of the above: efficient control with adversarial noise, general loss functions, unknown systems, and partial observation.
Joint work with Naman Agarwal, Brian Bullins, Karan Singh, Sham Kakade, Max Simchovitz, and Cyril Zhang.