(subject to change)
Wk. | Dates | Lecture slides (optional slides) | Reading (optional reading) | Due |
---|---|---|---|---|
1 | 9/29, 10/1 | Introduction; Agents; Search | R&N, 1,2,3.1 | PR0 |
2 | 10/4, 6, 8 | Informed Search ; Adversarial Search | R&N 3.2-end, 5.1-5.2; Search tool | |
3 | 10/11, 13, 15 | Expectimax ; (Local Search) | R&N 5.3-5.5, (4) | PR1 |
4 | 10/18, 20, 22 | Constraint Satisfaction Problems (CSPs) ; CSP Solvers; (CSP Bonus) | R&N 6.1-6.4, (6.5-end); CSP demo | HW1,PR2 |
5 | 10/25, 27, 29 | Markov Decision Processes (MDPs) ; MDP Solvers | R&N 17.1-17.3, (S&B 4.3-4.4) | HW2 |
6 | 11/1, 3, 5 | Passive Reinforcement Learning (RL); Active RL | R&N 22.1-22.3, (S&B 5.1-5.5) | HW3 |
7 | 11/8, 10, 12 | (Probability Review); Graphical Models ; Exact Inference | R&N (12), 13.1-13.3 | PR3 |
8 | 11/15, 17, 19 | Sampling Methods ; Independence | R&N 13.4-end; 14.1-14.2 | HW4 |
9 | 11/22, 24? | Markov Models | R&N 14.3 | HW5 |
10 | 11/29, 12/1, 3 | Approximate Markov Models; Intelligence | R&N 14.4-end; (S&B 14, 15) | PR4 |
11 | 12/6, 8, 10 | Fairness and Causality ; Wrap-up | Hardt's Note (B&H&N 1,2); R&N 27 | HW6 |
Individual assignments graded on correctness and due by 10pm on the day listed. Worth 50% of grade total. Make sure your answers are selected and visible when you submit them.
Homework (HW) | % of HW | Due | TA |
---|---|---|---|
1: Search [submit] | 1/6 | 10/18 | Mino & Vinitha |
2: CSPs [submit] | 1/6 | 10/29 | Skyler & Xinyue |
3: MDPs [submit] | 1/6 | 11/5 | Jackson & Mino |
4: Q-Learning [submit] | 1/6 | 11/17 | Jennifer & Chase |
5: Uncertainty [submit] | 1/6 | 11/24 | Skyler & Jackson |
6: HMMs [submit] | 1/6 | 12/10 | Chase & Jennifer |
Individual assignments graded on correctness and due by 10pm on the day listed. Worth 50% of grade total.
Projects (PR) | % of PR | Due | TA |
---|---|---|---|
0: Optional Warm-up | 0 | N/A | N/A |
1: Search | 1/4 | 10/13 | Vinitha |
2: Multi-agent | 1/4 | 10/22 | Xinyue |
3: Q-learning | 1/4 | 11/12 | Xinyue |
4: Inference & Filtering | 1/4 | 12/3 | Vinitha |
Optional, graded on completion, open for collaboration, and due at 10pm on the day of the subsequent lecture (no late days accepted). (Because we have 30 days of class and only 20 lectures we'll release the due dates as the lectures are completed.) Review the correct answers on gradescope or below after the submission date.
Each completed problem adds: (number of completed practice problems) * (10 / total number of practice problems) to your grade, which will then be renormalized. (E.g. completing all of them is worth 10% of grade, in which case written and programming assignments are worth 45% each.)
Links posted here and also on Gradescope.
Practice (PP) | Due |
---|---|
Lecture 02: Agents [Solutions] | 10/4 |
Lecture 03: Search [Solutions] | 10/6 |
Lecture 04: Informed Search [Solutions] | 10/11 |
Lecture 05: Adversarial Search [Solutions] | 10/15 |
Lecture 06: Expected Search [Solutions] | 10/18 |
(Optional: Local Search) [Solutions] | 10/18 |
Lecture 07: Constraint Satisfaction Problems (CSPs) [Solutions] | 10/22 |
Lecture 08: CSP Solvers [Solutions] | 10/25 |
Lecture 09: Markov Decision Processes (MDPs) [Solutions] | 10/29 |
Lecture 10: MDP Solvers [Solutions] | 11/01 |
Lecture 11: Passive Reinforcement Learning (RL) [Solutions] | 11/5 |
Lecture 12: Active RL [Solutions] | 11/8 |
(Lecture 13: Uncertainty) [Solutions] | 11/10 |
Lecture 13: Graphical Models [Solutions] | 11/12 |
Lecture 14: Bayes Nets [Solutions] | 11/15 |
Lecture 15: Sampling [Solutions] | 11/19 |
Lecture 16: d-separation [Solutions] | 11/22 |
Lecture 17: Markov Models [Solutions] | 11/29 |
Lecture 18: Particle Filtering [Solutions] | 12/3 |
Lecture 19: Intelligence | |
Lecture 20: Fairness and Causality |
There will be no curve and your grade will be as follows:
\[ \bigg \lceil \frac{ \frac{1}{12} \sum_{i=1}^{6} ( hw_i - \frac{1}{5} dl_{hw_i}) + \frac{1}{8} \sum_{i=1}^{4} (pr_i - \frac{1}{5} dl_{pr_i} ) + \frac{\sum_{i=1}^{|PP|} pp_i}{10|PP|}}{1 + \frac{\sum_{i=1}^{|PP|} pp_i}{10|PP|}} \times 40 \bigg \rceil / 10.0 ,\]
where each homework and project are \(hw_i, pr_i \in [0,1]\), each practice problem is \(pp \in \{0,1\}\), and each day late for an assignment \(dl_{hw,pr} \in \{0, 1, 2, 3, 4\}\), counting contiguous days off (holidays and weekends) as one and late days only applied to the first (and all subsequent) assignments after your total late days number greater than six.
(The one possible exception to this is that no student gets a 4.0 in which case we would then increase every student's grade by the difference between the highest scoring student and 4.0. We do not expect this to happen but will alert you if there is an assignment for which the max score is greater than the maximum achieved score which would be a proxy for such an event.)
We will try to schedule office hours to accommodate students' schedules and will offer at least 20 percent of office hours virtually. If you're still not able to make this time, please reach out to us on Ed.
We'll be enforcing room limits in office hours so for those of you unable to fit we may use a queue.
In addition to these regular hours, we will offer one additional virtual hour on the due date of each assignment. See the calendar for specifics.
For fastest response, contact us on Ed. Otherwise contact us over email at cse473-staff@cs.uw.edu .
Please use Ed for course related questions.
Lecture slides will be posted on this site before the relevant day. These are subject to revision of types typographic, syntactic, and semantic. We will alert the class if any major changes are made.
Lecture videos should upload to canvas automatically.
We welcome students from all backgrounds and adhere to the Allen Schoolâ€™s Inclusiveness Statement. If anything related to the course makes you feel unwelcome in any way, let the instructor know.
We are eager to provide necessary accommodations.
For disability accommodations, please see the UW resources
For religious accommodations, please see the UW resources