This is an old revision of the document!
In each lecture where there is new reading material, each student must create one “thought question” about the material. This question must be related to the reading and be thought-provoking. The question must also come with some answers. The more answers the better. If you manage to create a question regarding the topic you receive one point for the question. If it is thought-provoking or one can see that you spend some thought on it, you receive 2 points. So there are 2 points available each time you are supposed to hand in thought questions, giving you three possible grades: 0, 5 and 10. You should also show up in class with your thought questions as they will be used if there is some time left for discussion. Then a student will be selected randomly and should then read one of his/her questions to spark some discussion in class.
Every time there is some new reading material a project will appear in MySchool where you can hand your thought questions in.
Let´s take a look at some example thought questions from chapter 2(you will NOT hand in thought questions for chapter 2).
Examples of bad thought questions: Q: What is an agent A: An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators.
Q: What types of agents are there: A: Simple reflex, model-based, goal-based and utility-based
Examples of good thought questions: Q: Should the critic element of a learning agent be static or dynamic, meaning that it could change over time? A: It should be static so that all the experience that has been gathered doesn't become invalid. A: It should be dynamic because if the environment is dynamic, the critic should be able to adjust to it A: It should only change if its goals change.
Q: How can learning improve the types of agents mentioned in the chapter. A: Simple reflex agents could learn new if-then rules or change its own. Model-based agents could use learning to update their models. Goal-based agents could use learning to improve the plan search. Utility-based agents can use learning to improve its utility function
Q: Is it good for the programmer to know the environment which his/her agent will operate within? A: Yes, because it will create a better agent. A: No, because there is a danger of the agent's design being too dependent on the environment and its attributes.