-
Notifications
You must be signed in to change notification settings - Fork 0
/
valueIterationAgents.py
105 lines (87 loc) · 4.21 KB
/
valueIterationAgents.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
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
# valueIterationAgents.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://inst.eecs.berkeley.edu/~cs188/pacman/pacman.html
#
# 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).
import mdp, util
from learningAgents import ValueEstimationAgent
class ValueIterationAgent(ValueEstimationAgent):
"""
* Please read learningAgents.py before reading this.*
A ValueIterationAgent takes a Markov decision process
(see mdp.py) on initialization and runs value iteration
for a given number of iterations using the supplied
discount factor.
"""
def __init__(self, mdp, discount = 0.9, iterations = 100):
"""
Your value iteration agent should take an mdp on
construction, run the indicated number of iterations
and then act according to the resulting policy.
Some useful mdp methods you will use:
mdp.getStates()
mdp.getPossibleActions(state)
mdp.getTransitionStatesAndProbs(state, action)
mdp.getReward(state, action, nextState)
mdp.isTerminal(state)
"""
self.mdp = mdp
self.discount = discount
self.iterations = iterations
self.values = util.Counter() # A Counter is a dict with default 0
# Write value iteration code here
"*** YOUR CODE HERE ***"
for ite in range(iterations): ## repeat
stateValues=util.Counter() ## initial all values are 0
for state in mdp.getStates():
if mdp.isTerminal(state)==False: ##if not a terminal state
## maximizes the expected utility of each state
stateValues[state] = max([self.computeQValueFromValues(state, action) for action in mdp.getPossibleActions(state)])
self.values=stateValues
def getValue(self, state):
"""
Return the value of the state (computed in __init__).
"""
return self.values[state]
def computeQValueFromValues(self, state, action):
"""
Compute the Q-value of action in state from the
value function stored in self.values.
"""
"*** YOUR CODE HERE ***"
## calculate value of each state by that of its neighbor
Q_Values=0.0
for (nextState, prob) in self.mdp.getTransitionStatesAndProbs(state, action):
Q_Values+=prob*(self.mdp.getReward(state, action, nextState)+self.discount*self.getValue(nextState))
return Q_Values
def computeActionFromValues(self, state):
"""
The policy is the best action in the given state
according to the values currently stored in self.values.
You may break ties any way you see fit. Note that if
there are no legal actions, which is the case at the
terminal state, you should return None.
"""
"*** YOUR CODE HERE ***"
## The goal of MDP is to find an optimal policy which maximizes the expected utility of each
## stateThe goal of MDP is to find an optimal policy which maximizes the expected utility of each state
possibleActions=self.mdp.getPossibleActions(state)
actionValues=util.Counter()
for action in possibleActions:
actionValues[action] = self.computeQValueFromValues(state, action)
return actionValues.argMax()
def getPolicy(self, state):
return self.computeActionFromValues(state)
def getAction(self, state):
"Returns the policy at the state (no exploration)."
return self.computeActionFromValues(state)
def getQValue(self, state, action):
return self.computeQValueFromValues(state, action)