Safe Learning for Autonomous Systems

This lecture discusses challenges in control, safety, and coordination in uncertain dynamical systems, focusing on autonomous systems like autonomous cars. The instructor presents a model-based stochastic control approach, verification methods, and a paradigm shift towards learning and interaction. The lecture covers formulating safe learning problems, black-box information challenges, and a proposed safe learning approach. It also explores case studies in safe reinforcement learning and ongoing work in safe learning and control. The instructor delves into multi-agent systems formalized via game theory, Nash equilibria, learning in games, and learning Nash equilibria. The lecture concludes with discussions on bandit optimization, regret minimization, and model-based learning algorithms for Nash equilibria.