04-751 Reinforcement Learning

12 units, Carnegie Mellon University

This course provides a comprehensive introduction to the fundamentals and advanced topics of Reinforcement Learning RL, focusing on how autonomous agents can learn to make optimal decisions through interaction with an environment. Unlike supervised learning, RL focuses on learning from sparse, delayed rewardsa critical component for building intelligent engineering systems such as autonomous robots, smart grids, and adaptive manufacturing pipelines. The course bridges classical RL theory with modern Deep Learning techniques. Students will explore how to represent complex state spaces using neural networks and how to stabilize learning in highdimensional environments. A significant portion of the course is dedicated to the SimtoReal challenge, preparing students to deploy AI models in physical world scenarios relevant to the African context and global engineering standards.

Prerequisites: none listed

Courseweave needs JavaScript to show sections, workloads and planning tools.