-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathmodel.py
113 lines (95 loc) · 4.17 KB
/
model.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
106
107
108
109
110
111
112
113
import torch
import torch.nn as nn
import torch.nn.functional as F
class QNetwork(nn.Module):
"""Actor (Policy) Model."""
def __init__(self, state_size, action_size, seed, fc1_units=64, fc2_units=64):
"""Initialize parameters and build model.
Params
======
state_size (int): Dimension of each state
action_size (int): Dimension of each action
seed (int): Random seed
fc1_units (int): Number of nodes in first hidden layer
fc2_units (int): Number of nodes in second hidden layer
"""
super(QNetwork, self).__init__()
self.seed = torch.manual_seed(seed)
self.fc1 = nn.Linear(state_size, fc1_units)
self.fc2 = nn.Linear(fc1_units, fc2_units)
self.fc3 = nn.Linear(fc2_units, action_size)
def forward(self, state):
"""Build a network that maps state -> action values."""
x = F.relu(self.fc1(state))
x = F.relu(self.fc2(x))
return self.fc3(x)
class DuelingQNetwork(nn.Module):
"""Actor (Policy) Model."""
def __init__(self, state_size, action_size, seed, fc1_units=64, fc2_units=64):
"""Initialize parameters and build model.
Params
======
state_size (int): Dimension of each state
action_size (int): Dimension of each action
seed (int): Random seed
fc1_units (int): Number of nodes in first hidden layer
fc2_units (int): Number of nodes in second hidden layer
"""
super(DuelingQNetwork, self).__init__()
self.seed = torch.manual_seed(seed)
self.fc1 = nn.Linear(state_size, fc1_units)
self.fc2 = nn.Linear(fc1_units, fc2_units)
self.action_size = action_size
self.value_function_fc = nn.Linear(fc2_units, 1)
self.advantage_function_fc = nn.Linear(fc2_units, action_size)
def forward(self, state):
"""Build a network that maps state -> action values."""
x = F.relu(self.fc1(state))
x = F.relu(self.fc2(x))
value_function = self.value_function_fc(x)
advantage_function = self.advantage_function_fc(x)
return value_function + advantage_function - advantage_function.mean(1).unsqueeze(1).expand(x.size(0), self.action_size) / self.action_size
class ConvQNetwork(nn.Module):
"""Actor (Policy) Model."""
def __init__(self, state_size, action_size, seed, fc1_units=64, fc2_units=64):
"""Initialize parameters and build model.
Params
======
state_size (int): Dimension of each state
action_size (int): Dimension of each action
seed (int): Random seed
fc1_units (int): Number of nodes in first hidden layer
fc2_units (int): Number of nodes in second hidden layer
"""
super(QNetwork, self).__init__()
self.seed = torch.manual_seed(seed)
self.fc1 = nn.Linear(state_size, fc1_units)
self.fc2 = nn.Linear(fc1_units, fc2_units)
self.fc3 = nn.Linear(fc2_units, action_size)
def forward(self, state):
"""Build a network that maps state -> action values."""
x = F.relu(self.fc1(state))
x = F.relu(self.fc2(x))
return self.fc3(x)
class ConvDuelingQNetwork(nn.Module):
"""Actor (Policy) Model."""
def __init__(self, state_size, action_size, seed, fc1_units=64, fc2_units=64):
"""Initialize parameters and build model.
Params
======
state_size (int): Dimension of each state
action_size (int): Dimension of each action
seed (int): Random seed
fc1_units (int): Number of nodes in first hidden layer
fc2_units (int): Number of nodes in second hidden layer
"""
super(QNetwork, self).__init__()
self.seed = torch.manual_seed(seed)
self.fc1 = nn.Linear(state_size, fc1_units)
self.fc2 = nn.Linear(fc1_units, fc2_units)
self.fc3 = nn.Linear(fc2_units, action_size)
def forward(self, state):
"""Build a network that maps state -> action values."""
x = F.relu(self.fc1(state))
x = F.relu(self.fc2(x))
return self.fc3(x)