drawing

ECE 720A02 Robot Learning: Principles and Advances (fall term 2025)

Starting from the fall term 2025, this course will be ECE720 A02

Instructors:
Professor: Jun Jin
TAs: Yi Hu, hu19@ualberta.ca

Lectures: Monday Wednesday 12:30 to 13:50, ECERF W3-087

Office Hours: Wednesdays, 14:00 - 14:50, 11-365 Donadeo Innovation Centre For Engineering

Announcements

  • Welcome!
  • This is my third year teaching this course. Thanks for your interest. This year, we will make this course more interactive!

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) and foundation models (LLMs, decision transformers) for robotics.
  • 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 (40%)

  • There are four assignments. Each assignment is worth 10% of the final grade, for a total of 40%.
  • 2 math problems + 1 coding task (<10 lines) + 1 writing task about your project idea.

Read & Present what you've learned (6%)

  • 5-minute paper reading presentation.
  • Select a paper from our course reading list, and present what you have learned.

Think & Speak out your opinion (8%)

  • 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?

Review & Contribute your advice (6%)

  • Review the 1-course project report, mark your rating, and leave your review comments.

Final project (40%)

  • 1~5 students per project.
  • An in-depth study of a "small" but well-defined problem will be graded more favorably than a superficial study of a "large" problem. Therefore, please select a clearly defined and focused problem for your course project.
  • Think & Speak out your opinion (10%) is your best opportunity to study a "large" but interesting problem without putting too much time into it, but sharing your valuable thoughts!
  • Implement a learning algorithm (e.g., imitation learning, RL) of your choice to solve any decision-making tasks (robotics, games, control, prediction, etc.).
  • If you would like a starting code repository to simplify your project, we will provide one that includes: (1) a robotic simulator ready for training, and (2) a standard OpenAI Gym environment that can be used in a plug-and-play manner with existing open-source ML algorithm libraries (e.g., Stable Baselines).

  • 1/5 quality of presentation, 1/5 quality of writing of the final paper, 3/5 quality of the results themselves.

    • Extra points will be awarded to solutions that explore more advanced topics, e.g., inverse reinforcement learning (IRL), generalization, meta-learning, motion primitives, LLMs, etc.

  • Grading Rules:

    • Except for solo projects, grading will be based on the quality of the project’s completion, not on the number of students in a group.
    • A solo project will receive a 1.1 ratio bonus.
    • Each project report must explicitly document the contributions of all members.
    • In addition, each student must submit an individual evaluation form, which will be visible only to the instructor and the TA. This form requires both self-evaluation and evaluation of other group members’ contributions.
    • The course encourages collaborative, low-pressure teamwork. By default, all group members will receive the same grade.

    • However, if it becomes clear that a member has contributed significantly less than the others, that student’s grade may be adjusted using a ratio of 0.0 to 0.6, depending on the case. The instructor and TA will determine this adjustment based on the individual evaluation forms and the project report.

      • Such cases will be readily identifiable based on the consistency of the individual evaluation forms submitted by group members.

  • Grading Examples:

    • Equal Contribution (Group Project):

      • For a project group of four members, if the project receives a final score of 100, each member will receive 100 points. This contributes 100% × 40% = 40% toward the final course grade. In this case, all group members receive the full project credit.

    • Solo Project (Bonus):

      • If a project is completed individually, a 1.1 ratio bonus is applied. For example, if the project earns 100 points, the solo student will receive 100 × 1.1 = 110 points. Since the project accounts for 40% of the final grade, this translates to 110% × 40% = 44% toward the final grade (a 4% bonus).
      • The final project grade is based solely on the quality of the project, not on the number of members in a group.
      • Solo projects may require significantly more effort to achieve results comparable to group projects. To recognize this additional effort, a 1.1 ratio bonus will be applied to the final project score.
      • For example, if a solo project receives 80 points, the adjusted score will be 80 × 1.1 = 88 points. In contrast, a group project of higher quality that earns 100 points will award each member the full 100 points.
      • Therefore, while the solo project bonus offers some compensation, it does not replace the advantages of teamwork. Please consider carefully before deciding to pursue a solo project.

    • Partial Contribution (Group Project):

      • If a member contributes only partially compared to others, their grade will be adjusted accordingly. For example, if the project earns 100 points and one member’s contribution ratio is assessed at 0.5, that student’s calculation would be 100 × 0.5 = 50 points, which contributes 50% × 40% = 20% toward the final course grade.

    • Significantly Low Contribution (Group Project):

      • If a member contributes significantly less than the others (for example, the student does not attend group discussions, contribute to the report writing, participate in the presentation, or engage in the Q&A), that member may receive an adjustment ratio of 0.0. In this case, the calculation would be 100 × 0.0 = 0 points, which contributes 0% × 40% = 0% toward the final course grade. This means the student fails the project, which also results in failing the course.

  • Deadlines:

    • Oct 29: Project proposal DUE at midnight, Oct 29.

      • Nov 5: You will get project proposal feedback before Nov 5 (before the reading week).

    • Dec 03: Final Project report DUE Dec 03.

      • Dec 05: You will receive a project report from another group to review before Dec 05.
    • Dec 08: Final Project Presentation Dec 08.
    • Dec 12: Project Report Review DUE midnight, Dec 12

  • Important Milestones and Timing

    • Course Project Kick-off (Oct 1):

      • An ideal time to learn how to choose a project, understand grading criteria, and form your project team.

    • Reading Week (Nov 10–16):

      • No classes. You should receive feedback on your project proposal before Nov 5. Use Reading Week to make significant progress and finalize your project direction.

    • Final Project Aid (Nov 26):

      • A dedicated session to raise any remaining questions and seek guidance if your project has encountered challenges.

    • Project Finalization Week (Dec 1–7):

      • No classes. Use this time to complete your final project report and prepare for your presentation.

  • Teamwork Reminder:

    • Please respect your teammates and take responsibility for your role. Contribution, accountability, and collaboration are all essential aspects of successful teamwork.

Syllabus and materials

All slides will be released on the website after each lecture. All slides are open to the public and free to download.