CSE 573 - Introduction to Artificial Intelligence

University of Washington Department of Computer Science & Engineering

CSE 573 - Introduction to Artificial Intelligence - Winter 2016
Tues, Thurs 12:00-1:20pm in MGH 234 (moved to MGH 251 on feb 9 & 11)

CSE Home

About Us

Contact Info

Instructor: Dan Weld (weld at cs dot washington dot edu)
Office hours: Fri 10am in CSE 588 or by email TA: Chris Lin (chrislin at cs dot washington dot edu)
Office hours: Thu 1:30-2:30pm or Mon 2-3pm in CSE 382, or by email.
Cancelled 2/12-2/17 (Chris OOT).

Final Exam

Is here: (exam); it's due Friday at 10:30am. I prefer a hardcopy of the exam for ease of grading (deliver to CSE main office or under my door), but if that is a hardship you may email it to me and Chris. Here are the solutions.

Schedule

Date	Topics & Lecture Notes	Readings
January 5	Introduction, Agents (slides)	R&N Ch. 2; (Optional Ch 1)
January 7	Problem Spaces, Search (through A*) (slides)	R&N Ch. 3; try this cool interactive search visualization
January 12	Heuristic generation, pattern DBs, local search (slides)	R&N Ch. 4
January 14	Constraint Satisfaction I - formulation, backtracking, FC, AC, heuristics (slides)	R&N Ch. 6, sections 6.1-6.3
January 19	Constraint Satisfaction II - structure, local search (slides); SAT Solving (slides)	R&N sections 6.4, 6.5; Ch. 7
January 21	Adversarial search: mix-max, alpha-beta, expecti-max (slides)	R&N Ch. 5
January 26	Search redux (slides) MDPs, Value Iteration (pdf slides only) to page 26	R&N Ch. 16 thru 16.3; Ch 17 thru 17.2
January 28	MDPs, VI analysis & policy iteration (slides)	R&N 17.2 and 17.3
February 2	SSP MDPS; LAO* and LRTDP (review) (slides)	M&K Ch 4 thru 4.4.2
February 4	Reinforcement Learning (slides)	R&N Ch 21 thru 21.3
February 9	Approximate value functions (slides); Exploration / exploitation & Bandit algorithms (slides - see also 2/11)	R&N Sections 21.4 - 21.7; M&K Section 6.2 Tutorial on UCB
February 11	Finish bandits; Deep RL; (slides) UCT (optional: see slides 37+ here)	Playing Atari with Deep Reinforcement Learning
February 16	No Class
February 18	Hidden Markov Models (slides)	R&N Chapter 15 thru 15.3 (review 13 if necessary)
February 23	HMM Exact Inference & Particle Filters (slides)	R&N Sections 15.3 and 15.5
February 25	Bayes Networks (slides)	R&N Chapter 14 thru 14.4
March 1	UCT, POMDPs, POMCP (slides)	Monte Carlo Planning in Large POMDPs
March 3	POMDPS or BN Inference (slides)	R&N Sections 14.4 & 14.5
March 8	No Class
March 10	Grand Finale (plus BN Learning plus NELL) (slides)	R&N Chapter 20; [Carlson AAAI-10]

Programming Projects

This quarter, we will use the excellent Berkeley Pac-Man Projects originaly 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 0: Python Tutorial (Do not submit - Not Graded)
Problem Set 1: Search in Pac-Man due Monday 1/18 at 11:59 PM
Problem Set 2: Multi-Agent Pacman due Friday 1/29 at 11:59 PM
Problem Set 3: Reinforcement Learning due Sunday 2/14 at 11:59 PM
Problem Set 4: Inference due Monday 2/29 at 11:59 PM
Final Project: POMDPs due Sunday 3/13 at 11:59 PM

Project

Check here for info on the final project. Tentative group definitions and a one-sentence idea due TBD. Alternatively, you may complete the individual final programming assignment as the final project.

Take-home Final

Live Wed March 16; due 11:30am on Friday March 18. Open book & static Internet resources, but no discussions with other people besides Dan and Chris.

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 30% programming assignments, 10% paper reports, 10% class participation, 25% final exam, and 25% final project. (FInal project details are still in flux). Grades can be viewed in the gradebook.
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.
Programming assignments may be handed in late, but with a penalty of 10% of the maximum grade per day.

Communication

Please feel free to email Dan or Chris anytime or stop by their offices whenever convenient. Note: Dan is often in a panic, preparing with door shut immediately before class, but other times are great - or email for an appointment.
If you have comments of general interest, please use the discussion forum
For feedback to course staff, contact us directly or send an anonymous email.
Deposit homework in the dropbox

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