We would like to use a Q-learning agent for Pacman (as you did in PA3), but the state space for a large grid is too massive to hold in memory. To solve this, we will switch to feature-based representation of the Pacman game state (similar to PA3 Q10), where we assume that Q(s, a) can be expressed as a (weighted) linear combination of state-action features: Q(s, a)= Σωifi(s, a)

Required:
Suppose we design two features to represent the state (independent of actions): f (s) is the number of ghosts within one step of Pacman, and fp(s) is the number of food pellets within one step of Pacman. Note that we do not have any features dependent on a. Why might this be a bad idea?

b. xor is the correct answer

false , a, a, c b, ab

answer #2

darcy was working on a presentation on playing chess. because she chose the checkerboard animation for her slide title, she had to use the same animation for her bullet points.

this statement is   false

answer #4

4. when diego was done adding special effects to his presentation, he wanted to see how it would look to his audience. how did he do this?

b. he clicked on the slide show button.

we can see special effects that are added by clicking on slide show button

answer #5

d. she should use the same slide transition for each slide.

using same transition on every slide should be a better option.

answer #6

b. she matched transitions to her content.

c. she used consistent animations and transitions.

matching transitions to the content is a good practice.

and we should use static animations

answer#8

b. sound can distract the audience when it is overused.

e. sound cannot be used in presentation programs.