CS 4300/6300 Artificial Intelligence

Class Overview

This course will introduce the basic mathematics, algorithms, ideas and techniques underlying the design of intelligent computer systems that make decisions over time. A specific emphasis will be on the statistical and decision-theoretic modeling paradigm, with applications ranging from diagnosis to game-playing to robotics. This course is built around several multi-part programming projects, based on the game of Pacman. Coursework will consist of two kinds of assignments. Programming projects will be in Python. Written homeworks will be given most weeks.
Prerequisites: This course has substantial elements of both programming and mathematics, because these elements are central to modern AI. Prior programming experience is expected; although we don't expect that you know Python, we do expect you to be able to pick it up rapidly.
This will be a fun, but challenging class.

Class Schedule

Date Topic Slides Readings Assignment
Aug 19 Class Intro Slides RN 1.1, 2, Python Notes (Alan Kuntz) Project 0 (due Aug 22)
Aug 21 Uninformed Search Slides RN 3.1-3.4
Aug 26 Informed Search Slides RN 3.5-3.6
Aug 28 Game Playing: Adversarial Search Slides RN 5-5.3 HW 1 due (Aug 29)
Sept 2 Game Playing 2 Slides RN 5.4-5.5
Sept 4 Probability Refresher Slides RN 13-13.5 HW 2 Due
Sept 9 Intro to Markov Decision Processes Slides RN 17.1-17.2, SB 3, 4.4 Project 1 due
Sept 11 More MDPs Slides RN 17.3, SB 4.1-4.3
Sept 16 Monte Carlo Tree Search Slides SB 5, 8 intro, 8.6-8.12
Sept 18 Supervised Learning 1 Slides RN 18-18.5 (4th ed 19)
Sept 23 Supervised Learning 2 Slides RN 18.6-18.7 (4th Ed RN 19.6-19.7); GBC 6,7
Sept 25 Supervised Learning 3 GBC 8,9,10
Sept 30 Midterm Review Slides
Oct 2 Midterm
Oct 4-12 Fall Break
Oct 14 RL 1 Slides SB 6; RN 21.1-2 (4th ed RN 22.1-2)
Oct 16 RL 2 Slides SB 2,9,16.5; RN 22.3-22.4
Oct 21 RL 3 Slides SpinningUp Parts 1-3
Oct 23 RL 4 Slides AlphaGo paper
Oct 28 Bayes Nets 1 Slides RN 14-14.3
Oct 30 Bayes Nets 2 Slides RN 14.3
Nov 4 Bayes Nets 3 Slides RN 14.4
Nov 6 Bayes Nets 4 Slides 14.5
Nov 11 Decision diagrams, Markov chains Slides RN 16.5-6
Nov 13 HMMs 1 Slides RN 15.1-15.3
Nov 18 HMMs 2 Slides RN 15.5
Nov 20 Ethics Slides
Nov 25 Imitation Learning and IRL Slides
Dec 2 RLHF and LLMs Slides
Dec 4 Final exam review Slides
Dec 12 Final Exam In Classroom 10:30 am – 12:30 pm

Resources

We will have readings from books by Russell and Norvig (RN), Sutton and Barto (SB), Goodfellow, Bengio, and Courville (GBC); and Mykel Kochenderfer (MK). Here you can find links as well as other links you may find useful:

Homework and Exam Practice

You may find these example problems helpful in completing the homeworks and preparing for the exams