CSE 573 - Introduction to Artificial Intelligence

University of Washington Department of Computer Science & Engineering

CSE 573 - Introduction to Artificial Intelligence - Winter 2019
Mon, Wed 1:30-2:50pm in JHN 111

CSE Home

About Us

Contact Info

Instructor: Hanna Hajishirzi (Paul Allen Center 470) (hannaneh at washington dot edu)
Office hours: Wed 10:30am-11:30am, or by email
Contact: cse573-staff@cs.washington.edu TA: Dae Lee (dhlee4 at uw dot edu)
Office hours: Mon Noon-1:00pm in CSE 007, or by email.
James Ferguson (jfferg at uw dot edu)
Office hours: Tue 2:00pm-3:00pm in CSE 220, or by email.
Svetoslav Kolev (swetko at uw dot edu)
Office hours: Thu 1:00pm-2:00pm in CSE 220, or by email.

Schedule

Date	Topics & Lecture Notes	Readings	Assignments
January 7	Introduction and Agents (slides)	R&N Ch. 2; (Optional Ch 1)
January 9	Problem Spaces, Search (through A*) (slides)	R&N Ch. 3; try this cool interactive search visualization
January 14	Heuristic Generation, Local Search (slides)	R&N Ch. 4
January 16	Local Search/Adversarial Search - Minimax (slides: local search,adversarial search)	R&N Ch. 5	PS1 Due: Jan 18th
January 21	NO CLASS - Martin Luther King Day
January 23	Alpha-beta pruning/Complex Games (slides: Alpha-beta,Expectimax)	R&N Ch. 5
January 28	Expectimax/Complex Games/MDPs (slides: Expectimax,MDP)	R&N Ch 17 thru 17.3
January 30	Markov Decision Process(slides)	R&N Chapter 15 thru 15.3 (review 13 if necessary)	PS2 Due
February 4	CLASS CANCELLED
February 6	MDPs (Value Iteration)(slides)	R&N Ch 15 thru 15.3	Quiz 1
February 11	MDPs-Reinforcement Learning (Video)(slides: MDPs)(Calculations: MDP calculations )	R&N Ch 21 thru 21.3
February 13	Reinforcement Learning (Slides)	R&N Ch 21 thru 21.3 Playing Atari with Deep Reinforcement Learning
February 18	NO CLASS - Presidents Day
February 20	RL/Deep Reinforcement Learning ( Slides)	Playing Atari with Deep Reinforcement Learning	PS3 Due
February 25	Deep RL ( Slides)/Probabilistic Inference ( Slides)	Extra reading for Deep RL for interested students R&N Sections 15.3 and 15.5
February 27	HMMs/HMM Filtering (Slides)	R&N Chapter 14 thru 14.4, Equations for Part of Speech Tagging	Final Project Part 1 Due: Mar 1st
March 4	HMM Filtering (Slides)	R&N Sections 14.4 & 14.5	Paper report due
March 6	HMM Filtering (Slides)		PS4 Due: March 8th
March 11	Bayes Net Inference (Slides)	Quiz 2 (released March 8th, due March 11 before class)
March 13	Review
March 14 (12-2pm)	Poster presentation + Pizza		Final Project Due

Programming Projects

This quarter, we will use the excellent Berkeley Pac-Man Projects originally developed by John DeNero and Dan Klein. Please complete the versions listed below, as they differ in places from the originals. Use Python 2.x. Deposit homework in the dropbox.

Problem Set 1: Search in Pac-Man due Friday 1/18 at 11:59 PM
Problem Set 2: Alpha-beta pruning, minimax due Wednesday 1/30 at 11:59 PM
Problem Set 3: Reinforcement Learning due Wednesday 2/20 at 11:59 PM
Problem Set 4: Inference due Friday 3/8 at 11:59 PM

Final Project

For the final project, we will explore navigation and finding objects in scenes in the AI2-THOR simulator using deep reinforcement learning algorithms.

Part I: Setup and Experiments due Friday 3/1 at 11:59pm

You can also present your own project if it is related to the course material. Please submit a 1-page summary of your project proposal by the same deadline as the Part I report. due Friday 3/1 at 11:59pm.

Paper Report

Read the following papers for the paper report:

paper 1 (optional): https://www.aaai.org/Papers/AAAI/1993/AAAI93-117.pdf
paper 2 (required): https://arxiv.org/pdf/1312.5602.pdf

Check here for the details. Deposit the paper report to the dropbox

Textbooks

Required: Stuart Russell & Peter Norvig, Artificial Intelligence: A Modern Approach, Prentice-Hall, Third Edition (2009) [R&N].
Useful: Mausam, Andrey Kolobov. Planning with Markov Decision Processes: An AI Perspective Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan and Claypool Publishers. June 2012. (free online version if accessed from UW) [M&K]
Useful: Richard Sutton & Andrew Barto, Reinforcement Learning: An Introduction, MIT Press. (limited chapters; freely available online) [S&B]

Course Administration and Policies

Your grade will be 10% class participation, 10% paper reports, 30% homeworks, 25% quizes, and 25% project.
Assignments should be done individually unless otherwise specified. You may discuss the subject matter with other students in the class, but all final answers must be your own work. You are expected to maintain the utmost level of academic integrity in the course.
Late Policy (***EXCEPT FINAL PROJECT***): Each student has four penalty-free late day (UPDATED 02/27/2019) for the whole quarter, other than that any late submission will be penalized at a penalty of 10% of the maximum grade per day.
You can use penalty-free late days for Part I of the project. Penalty-free late days are not applicable to Final Project Part II and Quiz.

Communication

If you have comments of general interest, please use the discussion forum
We appreciate feedback throughout the quarter -- you can submit feedback through the Allen School’s anonymous feedback tool
Deposit homework in the dropbox

The Allen School of Computer Science & Engineering
University of Washington
Box 352350
Seattle, WA 98195-2350
(206) 543-1695 voice, (206) 543-2969 FAX