AI Systems and Robotics

1 Unit · Graduate

This course introduces reinforcement learning as an approach to intelligent systems. It reviews Markov decision processes, dynamic programming, temporal difference learning, and deep reinforcement learning. Students see how user feedback and reinforcement learning contribute to model development, with special reference to generative artificial intelligence. They develop, debug, tune, and visualize the model development process. They implement robotic process automation, personal assistants, and software agents, including conversational agents. This is a case study and project-based course with a substantial programming component. Recommended prior course: MSDS 458-DL Artificial Intelligence and Deep Learning.