Knowledge
of our earlier material is essential to understanding this material,
so you still need to know search methods, environmental/agent characteristics,
and knowledge representation techniques.
Chapters 11 (planning), 13, 14 through pg 507 (bayes nets), 17-17.3
(MDPs), 18-18.4(decision trees, ensembles), 20 through pg 718 (simple
amaximum likelihood learning), 20.5 (neural nets), 21-21.2(passive reinforcement
learning)
FINAL
Exam from Fall 2001 (PDF)
Problem 17.4 in book (MDP
practice from HW #6)
Solution
Another MDP/RL problem from 2004 exam
...and the solution.
Problem 20.11 (NN practice
from HW#6)
Solution |