Explore the cutting-edge developments in linear dynamical systems control during this 58-minute computer science seminar. Delve into the application of new machine learning methods that challenge classical control theory assumptions. Learn about efficient control techniques for systems with adversarial noise, general loss functions, unknown dynamics, and partial observation. Discover how these advancements are revolutionizing fields such as robotics, finance, engineering, and meteorology. Gain insights from speaker Elad Hazan of Princeton University as he presents findings from collaborative research efforts. Follow the seminar's progression through topics including optimal control, dynamics, loss functions with memory, and the concept of minimum regret in non-stochastic control problems.