-
Notifications
You must be signed in to change notification settings - Fork 0
/
analysis.py
72 lines (63 loc) · 2.18 KB
/
analysis.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
# analysis.py
# -----------
# Licensing Information: You are free to use or extend these projects for
# educational purposes provided that (1) you do not distribute or publish
# solutions, (2) you retain this notice, and (3) you provide clear
# attribution to UC Berkeley, including a link to http://ai.berkeley.edu.
#
# Attribution Information: The Pacman AI projects were developed at UC Berkeley.
# The core projects and autograders were primarily created by John DeNero
# (denero@cs.berkeley.edu) and Dan Klein (klein@cs.berkeley.edu).
# Student side autograding was added by Brad Miller, Nick Hay, and
# Pieter Abbeel (pabbeel@cs.berkeley.edu).
######################
# ANALYSIS QUESTIONS #
######################
# Set the given parameters to obtain the specified policies through
# value iteration.
def question2a():
"""
Prefer the close exit (+1), risking the cliff (-10).
"""
answerDiscount = 0.1
answerNoise = 0
answerLivingReward = -0.2
return answerDiscount, answerNoise, answerLivingReward
def question2b():
"""
Prefer the close exit (+1), but avoiding the cliff (-10).
"""
answerDiscount = 0.25
answerNoise = 0.2
answerLivingReward = 0.0
return answerDiscount, answerNoise, answerLivingReward
def question2c():
"""
Prefer the distant exit (+10), risking the cliff (-10).
"""
answerDiscount = 1
answerNoise = 0
answerLivingReward =-1
return answerDiscount, answerNoise, answerLivingReward
def question2d():
"""
Prefer the distant exit (+10), avoiding the cliff (-10).
"""
answerDiscount = 0.9
answerNoise = 0.1
answerLivingReward = 0.9
return answerDiscount, answerNoise, answerLivingReward
def question2e():
"""
Avoid both exits and the cliff (so an episode should never terminate).
"""
answerDiscount = 0.9
answerNoise = 0
answerLivingReward = 2
return answerDiscount, answerNoise, answerLivingReward
if __name__ == '__main__':
print('Answers to analysis questions:')
import analysis
for q in [q for q in dir(analysis) if q.startswith('question')]:
response = getattr(analysis, q)()
print(' Question %s:\t%s' % (q, str(response)))