Welcome

Prerequisites

• Familiarity with mathematical proofs, probability, algorithms, and linear algebra; ability to implement algorithmic ideas in code.
• Key Machine Learning courses that can build your background: ECE 447, ECE 449, COMPUT 466/566. If your foundations are rusty, we recommend you refresh them through those courses.
• All graduate students are welcome to register.

Class Goals

• Learn the math and algorithms in modern machine learning based robotic systems.
• Grasp an overall picture of state-of-the-art literature in robot learning, with a special focus on robotic reinforcement learning (RL), robot learning from human preference, multi-task learning and continual learning (CL).
• An intended side-effect of the course is to generally strengthen your expertise in these areas.
• Be able to understand research papers in the field of robotics:
  • Main conferences: ICRA, IROS, RSS, CoRL, NeurIPS, ICML, ISER, ISRR.
  • Main journals: IJRR, T-RO, Autonomous Robots, RA-L.
• Try out some ideas/extensions of your own.
• Note: The focus of this course is on math and algorithms. We will not study the mechanical or electrical design of robots.

Grading

• Assignments (50%)

  • There are six assignments. Each assignment has different weights towards the final sum of weights of 50%:

    Assignment	Topic	Weight
    Assn. 1	MDP Basics	6%
    Assn. 2	PPO I	10%
    Assn. 3	PPO II	10%
    Assn. 4	SAC	10%
    Assn. 5	SF and IRL	8%
    Assn. 6	CRL Paper Reading	6%
    Total		50%

  • The PPO I, PPO II, and SAC assignments require students to write code in Python. A basic understanding of Python and how to train neural networks using PyTorch is required.

• Read & Present what you've learned (5%)

  • 5-minute paper reading presentation.
    • Select a paper from our course reading list, and present what you have learned.
    • ECE562 Reading List.pdf (revised on Sep 2, 2026 by Dr. Jun Jin)

• Think & Speak out your opinion (5%)

  • 5 min machine learning street talk.
    • Share your opinion on machine learning in robotics. Do these methods excite you, or do you feel they rely on overly simplistic or unrealistic assumptions? What problems are you curious about? Do you have better solutions in mind? And if you were given $1 million research fund, what kind of project would you pursue?

• Final Exam (40%)

  • Date: TBD, usually during the week of December 7–11. The exact date and time will be announced once the official examination schedule is available.
  • Format: The final exam will be closed-book and consist entirely of multiple-choice questions (MCQs).
  • Purpose: The questions will assess your conceptual understanding, analytical reasoning, and ability to apply deep reinforcement learning methods. They may include scenarios, equations, short calculations, learning curves, and code interpretation.
  • Why MCQs? A sufficient number of carefully designed MCQs can provide broad and reliable coverage of the course learning outcomes. The resulting grades can also provide a meaningful distinction among different levels of student understanding, consistent with the University’s grade descriptors.
  • Preparation: Attend lectures, participate in-class Q&As and participate in the course review sessions. The reviews will help you consolidate important concepts and understand the scope and expectations of the final exam.

Reading List

• ECE562 Reading List.pdf (revised on Sep 2, 2026 by Dr. Jun Jin)

Syllabus

ECE562_Lecture_Topics_Fall_2026.pdf (PDF)

** Note: You need to use your ualberta email account to download the slides. If you find problems accessing the slides pdf, click on your google account, switch to your ualberta email account, it will work.

Lecture schedule: open the live schedule in Google Sheets. If the embedded schedule below does not load in your browser, use this link.

---

The University of Alberta, its buildings, labs and research stations are primarily located on the territory of the Néhiyaw (Cree), Niitsitapi (Blackfoot), Métis, Nakoda (Stoney), Dene, Haudenosaunee (Iroquois) and Anishinaabe (Ojibway/ Saulteaux), lands that are now known as part of Treaties 6, 7 and 8 and homeland of the Métis. The University of Alberta respects the sovereignty, lands, histories, languages, knowledge systems and cultures of all First Nations, Métis and Inuit nations.