forked from muupan/dqn-in-the-caffe
-
Notifications
You must be signed in to change notification settings - Fork 23
/
Copy pathdqn.prototxt
151 lines (151 loc) · 2.61 KB
/
dqn.prototxt
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
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
layers {
name: "frames_input_layer"
type: MEMORY_DATA
top: "frames"
top: "dummy1"
memory_data_param {
batch_size: 32
channels: 4
height: 84
width: 84
}
}
layers {
name: "target_input_layer"
type: MEMORY_DATA
top: "target"
top: "dummy2"
memory_data_param {
batch_size: 32
channels: 18
height: 1
width: 1
}
}
layers {
name: "filter_input_layer"
type: MEMORY_DATA
top: "filter"
top: "dummy3"
memory_data_param {
batch_size: 32
channels: 18
height: 1
width: 1
}
}
layers {
name: "silence_layer"
type: SILENCE
bottom: "dummy1"
bottom: "dummy2"
bottom: "dummy3"
}
layers {
name: "conv1_layer"
type: CONVOLUTION
bottom: "frames"
top: "conv1"
blobs_lr: 1 # learning rate multiplier for the filters
blobs_lr: 2 # learning rate multiplier for the biases
weight_decay: 1 # weight decay multiplier for the filters
weight_decay: 0 # weight decay multiplier for the biases
convolution_param {
num_output: 16
kernel_size: 8
stride: 4
weight_filler {
type: "gaussian"
std: 0.01
}
}
}
layers {
name: "conv1_relu_layer"
type: RELU
bottom: "conv1"
top: "conv1"
relu_param {
negative_slope: 0.01
}
}
layers {
name: "conv2_layer"
type: CONVOLUTION
bottom: "conv1"
top: "conv2"
blobs_lr: 1 # learning rate multiplier for the filters
blobs_lr: 2 # learning rate multiplier for the biases
weight_decay: 1 # weight decay multiplier for the filters
weight_decay: 0 # weight decay multiplier for the biases
convolution_param {
num_output: 32
kernel_size: 4
stride: 2
weight_filler {
type: "gaussian"
std: 0.01
}
}
}
layers {
name: "conv2_relu_layer"
type: RELU
bottom: "conv2"
top: "conv2"
relu_param {
negative_slope: 0.01
}
}
layers {
name: "ip1_layer"
type: INNER_PRODUCT
bottom: "conv2"
top: "ip1"
inner_product_param {
num_output: 256
weight_filler {
type: "gaussian"
std: 0.01
}
}
}
layers {
name: "ip1_relu_layer"
type: RELU
bottom: "ip1"
top: "ip1"
relu_param {
negative_slope: 0.01
}
}
layers {
name: "ip2_layer"
type: INNER_PRODUCT
bottom: "ip1"
top: "q_values"
inner_product_param {
num_output: 18
weight_filler {
type: "gaussian"
std: 0.01
}
}
}
layers {
name: "eltwise_layer"
type: ELTWISE
bottom: "q_values"
bottom: "filter"
top: "filtered_q_values"
eltwise_param {
operation: PROD
}
}
layers {
name: "loss"
type: EUCLIDEAN_LOSS
bottom: "filtered_q_values"
bottom: "target"
top: "loss"
}