-
Notifications
You must be signed in to change notification settings - Fork 0
/
ddpg_model.py
141 lines (121 loc) · 5.56 KB
/
ddpg_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
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
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
def hidden_init(layer):
fan_in = layer.weight.data.size()[0]
lim = 1. / np.sqrt(fan_in)
return (-lim, lim)
# neural net structure based on this thread: https://knowledge.udacity.com/questions/277763
class Actor(nn.Module):
"""Actor (Policy) Model."""
def __init__(self, state_size, action_size, seed, fc1_units=256):
"""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(Actor, self).__init__()
self.seed = torch.manual_seed(seed)
self.fc1 = nn.Linear(state_size, fc1_units)
self.batch_norm1 = nn.BatchNorm1d(fc1_units)
self.fc2 = nn.Linear(fc1_units, action_size)
self.reset_parameters()
def reset_parameters(self):
self.fc1.weight.data.uniform_(*hidden_init(self.fc1))
self.fc2.weight.data.uniform_(-3e-3, 3e-3)
def forward(self, state):
"""Build an actor (policy) network that maps states -> actions."""
x = F.relu(self.batch_norm1(self.fc1(state)))
return F.tanh(self.fc2(x))
# class Actor(nn.Module):
# """Actor (Policy) Model."""
# def __init__(self, state_size, action_size, seed, fc1_units=256, fc2_units=128):
# """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(Actor, 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)
# self.reset_parameters()
# def reset_parameters(self):
# self.fc1.weight.data.uniform_(*hidden_init(self.fc1))
# self.fc2.weight.data.uniform_(*hidden_init(self.fc2))
# self.fc3.weight.data.uniform_(-3e-3, 3e-3)
# def forward(self, state):
# """Build an actor (policy) network that maps states -> actions."""
# x = F.relu(self.fc1(state))
# x = F.relu(self.fc2(x))
# return F.tanh(self.fc3(x))
class Critic(nn.Module):
"""Critic (Value) Model."""
def __init__(self, state_size, action_size, seed, fcs1_units=256, fc2_units=256, fc3_units=128):
"""Initialize parameters and build model.
Params
======
state_size (int): Dimension of each state
action_size (int): Dimension of each action
seed (int): Random seed
fcs1_units (int): Number of nodes in the first hidden layer
fc2_units (int): Number of nodes in the second hidden layer
"""
super(Critic, self).__init__()
self.seed = torch.manual_seed(seed)
self.fcs1 = nn.Linear(state_size, fcs1_units)
self.fc2 = nn.Linear(fcs1_units+action_size, fc2_units)
self.batch_norm1 = nn.BatchNorm1d(fc2_units)
self.fc3 = nn.Linear(fc2_units,fc3_units)
self.fc4 = nn.Linear(fc3_units, 1)
self.reset_parameters()
def reset_parameters(self):
self.fcs1.weight.data.uniform_(*hidden_init(self.fcs1))
self.fc2.weight.data.uniform_(*hidden_init(self.fc2))
self.fc3.weight.data.uniform_(*hidden_init(self.fc3))
self.fc4.weight.data.uniform_(-3e-3, 3e-3)
def forward(self, state, action):
"""Build a critic (value) network that maps (state, action) pairs -> Q-values."""
xs = F.leaky_relu(self.fcs1(state))
x = torch.cat((xs, action), dim=1)
x = F.leaky_relu(self.batch_norm1(self.fc2(x)))
x = F.leaky_relu(self.fc3(x))
return self.fc4(x)
# class Critic(nn.Module):
# """Critic (Value) Model."""
# def __init__(self, state_size, action_size, seed, fcs1_units=256, fc2_units=128):
# """Initialize parameters and build model.
# Params
# ======
# state_size (int): Dimension of each state
# action_size (int): Dimension of each action
# seed (int): Random seed
# fcs1_units (int): Number of nodes in the first hidden layer
# fc2_units (int): Number of nodes in the second hidden layer
# """
# super(Critic, self).__init__()
# self.seed = torch.manual_seed(seed)
# self.fcs1 = nn.Linear(state_size, fcs1_units)
# self.fc2 = nn.Linear(fcs1_units+action_size, fc2_units)
# self.fc3 = nn.Linear(fc2_units, 1)
# self.reset_parameters()
# def reset_parameters(self):
# self.fcs1.weight.data.uniform_(*hidden_init(self.fcs1))
# self.fc2.weight.data.uniform_(*hidden_init(self.fc2))
# self.fc3.weight.data.uniform_(-3e-3, 3e-3)
# def forward(self, state, action):
# """Build a critic (value) network that maps (state, action) pairs -> Q-values."""
# xs = F.relu(self.fcs1(state))
# x = torch.cat((xs, action), dim=1)
# x = F.relu(self.fc2(x))
# return self.fc3(x)