ECE 720 A02 - Robot Learning: Principles and Advances

Term: Fall 2025 (Previous offerings: Winter 2024, Winter 2025 as ECE 720 B01 [Backlog Website])

This advanced graduate course covers the foundations and latest breakthroughs in robot learning. The curriculum is structured around:

• 60% Reinforcement Learning: Markov Decision Processes, value-based and policy-gradient methods.
• 20% Continual Learning: Techniques for building agents that learn and adapt over time without forgetting.
• 20% Embodied AI: Grounding intelligence in physical robotic systems and multi-modal interaction.

Note: This course will be offered until further notice, currently scheduled through Fall 2025.

ENCMP 100 - Computer Programming for Engineers

Audience: 1st Year Undergraduate Engineering students

I serve as part of a coordinated flagship teaching team for this foundational course. In a high-impact environment with approximately 280 students per classroom, we introduce the essential principles of computation and programming to the entire Faculty of Engineering. I find great joy in mentoring students at the very beginning of their engineering journey.

ECE 562 - Deep Reinforcement Learning for Robotics

Commencing: Fall 2026

ECE 562 is designed for students to master the essentials of Machine Learning (ML) and Reinforcement Learning (RL) within a single semester. The course provides comprehensive coverage of:

• Foundational Review: Linear algebra, probability, and statistics.
• ML Basics: Supervised learning, neural networks, and backpropagation.
• Deep RL Algorithms: Value-based, policy gradient, and actor–critic methods.
• Model-based RL and Inverse RL.
• Temporal abstraction and Options for skill discovery.
• Real-world applications of RL in complex robotic systems.

MCTR 370 - Machine Learning for Mechatronics

Commencing: Spring/Summer 2027

A brand-new course developed for the first cohort of the Mechatronics and Robotics Engineering Cooperative Program. This course bridges the gap between theoretical ML and practical robotics, featuring:

• Up-to-date ML topics from basics to deep neural network architectures.
• Supervised, Unsupervised, and Reinforcement Learning algorithms.
• Hands-on lab sessions focused on training neural networks and deploying models to work in real robotic systems.