CS 175: Project in Artificial Intelligence

Winter 2025

Schedule

Note: the planned schedule is subject to change. Course materials will occasionally be added above.

Course logistics

• When: Wednesdays at 5pm–7:50, only in weeks 1 and 2.
• Where: SE2 1304.
• Format:
  • Lectures during the first couple of weeks will introduce reinforcement learning, suggested project platforms, and the course expectations and evaluation criteria.
    • These lectures will be in-person but recorded / online resources will also be available; please keep up to date with the schedule above.
    • Lecture attendance is optional but an exact online replica of the in-person materials cannot be guaranteed.
  • After the introductory lectures, project teams will meet separately at times they will schedule.
  • Each team will meet periodically with the instructor and/or TA.
    • In-person and virtual meeting slots will be posted throughout the quarter.
    • The minimum requirement is to meet the course staff once by week 5 and once more by week 9; however, this is way too little, and more frequent meetings are strongly encouraged.
  • To get you started, 2 exercises will be due on weeks 3 and 4.
  • Project proposals and reports will be due on weeks 3, 7, and 10.
  • During week 11, the class will meet again for teams to present their projects.
  • There will be no discussion section meetings.
• Ed Discussion:
  • Please use the forum for course-related discussions.
  • Important course announcements will be posted there as well (not on Canvas).
  • Please use the forum (not email) to privately message course staff about course-related matters.
  • Please note that the identity of anonymous posters is visible to the course staff.
• Gradescope:
  • Instructions for exercises, proposals, and reports will be posted on this page.
  • They should be submitted on Gradescope.
  • We encourage submitting PDF files, and particularly writing them in LaTeX.
• Canvas:
  • Canvas will only be used to manage teams and report grades.
• Instructor: Prof. Roy Fox
  • Office hours: in-person or on zoom.
  • More times available by request.
• Teaching assistant: JB Lanier
  • Office hours.

Grading policy

• Exercises: 10% (individual)
  • Late submission: 3 grace days total, for both assignments, per person
• Project proposal: 10% (team)
• Progress report: 20% (team)
• Final report: 40% (team + individual component)
  • Late submission: 5 grace days total, for all project submissions, per team
• Project presentation: 15% (team)
• Participation (meetings, forum, evaluations): 5% (individual)
• No exams

Resources

Compute Resources

• HPC3
• ICS Openlab

Past projects

• Fall’19
• Fall’20
• Winter’21

RL tutorials

• Basic tutorial and worked examples
• Blog series providing gentle intro
• Intro to DeepRL algorithms

RL libraries

• RLlib
• Baselines
• MushroomRL
• Coach

Courses

• Roy Fox (UCI)
• David Silver (UCL)
• Sergey Levine (Berkeley)
• Dimitri Bertsekas (MIT)

Books

• Richard Sutton & Andrew Barto
• Vincent François-Lavet et al.
• Csaba Szepesvári

Academic integrity

Don’t cheat. Academic dishonesty includes partially copying answers from other students or online resources, allowing other students to partially copy your answers, communicating information about exam answers to other students during an exam, or attempting to use disallowed notes or other aids during an exam. The biggest downside to such behavior is that it necessarily becomes part of who you are — a dishonest person. Additionally painful, such behavior is easier to identify than you think, and consequences can be severe, including failing this course. Trust me, it's not worth it.