Courses, mentorship, and educational materials in machine learning and reinforcement learning.
Offered as CS 401R at BYU in Fall 2026. A problem-first introduction to RL that starts from a concrete goal and progressively relaxes what you can assume about your data, introducing formalism...
Learn MoreBuilding a research group at BYU around sequential decision making under partial observability, delayed feedback, and irreversibility. Recruiting graduate students whose curiosity, not a fixed agenda, sets the direction.
Learn MoreBYU Undergraduates take on real open questions, not literature summaries — and build new methods to directly address the research problems they face.
Learn MoreComprehensive undergraduate introduction to supervised learning, unsupervised learning, and practical ML skills, pairing theory with hands-on implementation of core algorithms.
Learn MoreA second course in RL, focused on deep reinforcement learning. Follows the arc of Graesser & Keng's Foundations of Deep Reinforcement Learning, deriving in full the mathematics that the introductory course only...
Learn MoreA graduate survey of open questions in RL, organized around the assumptions the classical formulation quietly makes — a given state, a stationary task, a network that can still learn, an agent...
Learn More