| Week | Date | Work | Slides | Topic |
| 1 | Mon 3/30 | Project 0 assigned |
Intro |
Introduction, Agents Chapters 1 and 2 |
| Wed 4/1 | Search |
Problem Spaces & Blind Search Chapter 3.1 - 3.4 |
||
| Fri 4/3 | Project 1 Assigned | Heuristic Search |
Best-First, Uniform-Cost, Greedy, and A* Search Chapter 3.5 - 3.7 |
|
| 2 | Mon 4/6 | Heuristic Search and Robotics path planning | Heuristic search, path planning in robotics | |
| Wed 4/8 | Constraint Satisfaction |
Definition,
contraint propagation, backtracking Chapter 6, Sections 6.1 - 6.3 |
||
| Fri 4/10 |
CSP continued,
ordering Chapter 6, Sections 6.1 - 6.3 |
|||
| 3 | Mon 4/13 | CSP2, Local Search |
CSP continued,
structure, local search Chapter 6, Sections 6.4 - 6.5, Section 4.1 |
|
| Wed 4/15 | Adversarial-search |
Adversarial
search, minimax, alpha-beta Chapter 5, Sections 5.1 - 5.3 |
||
| Fri 4/17 | Uncertainty |
Expectimax,
uncertainty, utilities Chapter 5, Sections 5.4, 5.5, 5.7, 5.9 Chapter 16, Sections 16.1-16.3 |
||
| 4 | Mon 4/20 | Project 1 Due (9:30AM) Project 2 Assigned |
MDP |
Utilities, Markov
Decision Processes Chapter 17, Sections 17.1, 17.2 |
| Wed 4/22 | MDP value iteration |
MDP, value iteration Chapter 17, Sections 17.1-17.2 |
||
| Fri 4/24 | MDP policy iteration |
MDP, policy iteration Chapter 17, Section 17.2-17.3 |
||
| 5 | Mon 4/27 | RL1 |
Reinforcement
learning, passive, active Chapter 21, Section 21.1, 21.2 |
|
| Wed 4/29 | RL2 |
Reinforcement
learning, exploration, generalization Chapter 21, Section 21.3, 21.4 |
||
| Fri 5/1 |
Project 2 Due (9:30AM) Project 3 Assigned |
RL-IOC |
Reinforcement
learning, inverse optimal control Chapter 21, Section 21.5 |
|
| 6 | Mon 5/4 | Probabilities |
Probabilities Chapter 13, Section 13.1 - 13.3 |
|
| Wed 5/6 | Midterm |
14au midterm (solutions) 12sp final (trimmed to relevant topics) (solutions) (ignore extra) Additional Practice Midterms Midterm solution | ||
| Fri 5/8 | Markov Models |
Probabilities/Markov Models Chapter 13, Sections 13.3/4/5/7, Chapter 15. |
||
| 7 | Mon 5/11 |
Probabilities/Markov Models continued |
||
| Wed 5/13 | HMM |
Hidden Markov Models (HMMs) Chapter 15, Section 15.3 |
||
| Fri 5/15 | Particle filters |
Particle Filters Chapter 15, Section 15.5 |
||
| 8 | Mon 5/18 |
Project 3 Due (9:30AM) Project 4 Assigned |
PF, Kalman filter |
Rao-Blackwellized
Particle Filters, Kalman Filters Chapter 15, Section 15.4 |
| Wed 5/20 | Bayes nets |
Bayes Nets Chapter 14, Section 14.1-2 |
||
| Fri 5/22 | Bayes nets 2 |
Bayes Nets: Independence Chapter 14, Section 14.2 |
||
| 9 | Mon 5/25 | Memorial Day (No Class) | ||
| Wed 5/27 | BN Inference |
Bayes Nets: Inference Chapter 14, Section 14.4 |
||
| Fri 5/29 | Project 4 Due (9:30AM) | BN Learning |
Bayes Nets: Learning Chapter 20 (especially 20.3) |
|
| 10 | Mon 6/1 |
Homework
5 assigned |
Gaussian
Processes |
Gaussian Processes |
| Wed 6/3 | ||||
| Fri 6/5 | Homework 5 due (9:30AM) |
Conclusion |
Conclusion |
|
| Finals | Wed 6/10 |
Final Exam 8:30-10:20http://www.washington.edu/students/reg/S2015exam.html |
473 14au
(solutions) (all) Berkeley 188: 188 14sp (solutions) (Ignore: 2d, 2e, 4e, 4f, 4g, 5, 7biii, 9) 188 13au (solutions) (Ignore: 5c, 5d, 8, 9c, 9d) |
|