Must be in the Graduate Program in Computer Science. All other graduate students must request permission.

AI-based agents need to operate in complex environments to make sequences of decisions to achieve some known goal. Many learning frameworks for sequential decision making exist, including reinforcement learning, imitation learning, learning from instructions, and others. In this course we will cover the foundations of all these methods, building up to modern AI-based agents that are enabled by large foundation models such as large language models and large vision/language models.