-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtetris_ddqn_torch.py
169 lines (135 loc) · 6.13 KB
/
tetris_ddqn_torch.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
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
import os
import numpy as np
import torch as T
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
class ReplayBuffer():
def __init__(self, max_size, input_shape):
self.mem_size = max_size
self.mem_cntr = 0
self.state_memory = np.zeros((self.mem_size, *input_shape),
dtype=np.float32)
self.new_state_memory = np.zeros((self.mem_size, *input_shape),
dtype=np.float32)
self.action_memory = np.zeros(self.mem_size, dtype=np.int64)
self.reward_memory = np.zeros(self.mem_size, dtype=np.float32)
self.terminal_memory = np.zeros(self.mem_size, dtype=np.uint8)
def store_transition(self, state, action, reward, state_, done):
index = self.mem_cntr % self.mem_size
self.state_memory[index] = state
self.new_state_memory[index] = state_
self.action_memory[index] = action
self.reward_memory[index] = reward
self.terminal_memory[index] = done
self.mem_cntr += 1
def sample_buffer(self, batch_size):
max_mem = min(self.mem_cntr, self.mem_size)
batch = np.random.choice(max_mem, batch_size, replace=False)
states = self.state_memory[batch]
actions = self.action_memory[batch]
rewards = self.reward_memory[batch]
states_ = self.new_state_memory[batch]
terminal = self.terminal_memory[batch]
return states, actions, rewards, states_, terminal
class DuelingDeepQNetwork(nn.Module):
def __init__(self, lr, n_actions, name, input_dims, chkpt_dir):
super(DuelingDeepQNetwork, self).__init__()
self.checkpoint_dir = chkpt_dir
self.checkpoint_file = os.path.join(self.checkpoint_dir, name)
self.fc1 = nn.Linear(*input_dims, 512)
self.V = nn.Linear(512, 1)
self.A = nn.Linear(512, n_actions)
self.optimizer = optim.Adam(self.parameters(), lr=lr)
self.loss = nn.MSELoss()
self.device = T.device('cuda:0' if T.cuda.is_available() else 'cpu')
self.to(self.device)
def forward(self, state):
flat1 = F.relu(self.fc1(state))
V = self.V(flat1)
A = self.A(flat1)
return V, A
def save_checkpoint(self):
print('... saving checkpoint ...')
T.save(self.state_dict(), self.checkpoint_file)
def load_checkpoint(self):
print('... loading checkpoint ...')
self.load_state_dict(T.load(self.checkpoint_file))
class Agent():
def __init__(self, gamma, epsilon, lr, n_actions, input_dims,
mem_size, batch_size, eps_min=0.05, eps_dec=5e-7,
replace=1000, chkpt_dir='tmp/dueling_ddqn'):
self.gamma = gamma
self.epsilon = epsilon
self.lr = lr
self.n_actions = n_actions
self.input_dims = input_dims
self.batch_size = batch_size
self.eps_min = eps_min
self.eps_dec = eps_dec
self.replace_target_cnt = replace
self.chkpt_dir = chkpt_dir
self.action_space = [i for i in range(self.n_actions)]
self.learn_step_counter = 0
self.memory = ReplayBuffer(mem_size, input_dims)
self.q_eval = DuelingDeepQNetwork(self.lr, self.n_actions,
input_dims=self.input_dims,
name='ddqn_q_eval',
chkpt_dir=self.chkpt_dir)
self.q_next = DuelingDeepQNetwork(self.lr, self.n_actions,
input_dims=self.input_dims,
name='ddqn_q_next',
chkpt_dir=self.chkpt_dir)
def choose_action(self, observation):
if np.random.random() > self.epsilon:
state = T.tensor([observation],dtype=T.float).to(self.q_eval.device)
_, advantage = self.q_eval.forward(state)
action = T.argmax(advantage).item()
else:
action = np.random.choice(self.action_space)
return action
def store_transition(self, state, action, reward, state_, done):
self.memory.store_transition(state, action, reward, state_, done)
def replace_target_network(self):
if self.learn_step_counter % self.replace_target_cnt == 0:
self.q_next.load_state_dict(self.q_eval.state_dict())
def decrement_epsilon(self):
self.epsilon = self.epsilon - self.eps_dec \
if self.epsilon > self.eps_min else self.eps_min
def save_models(self):
self.q_eval.save_checkpoint()
self.q_next.save_checkpoint()
def load_models(self):
self.q_eval.load_checkpoint()
self.q_next.load_checkpoint()
def learn(self):
if self.memory.mem_cntr < self.batch_size:
return
self.q_eval.optimizer.zero_grad()
self.q_next.optimizer.zero_grad()
self.replace_target_network()
state, action, reward, new_state, done = \
self.memory.sample_buffer(self.batch_size)
states = T.tensor(state).to(self.q_eval.device)
rewards = T.tensor(reward).to(self.q_eval.device)
dones = T.tensor(done).to(self.q_eval.device)
actions = T.tensor(action).to(self.q_eval.device)
states_ = T.tensor(new_state).to(self.q_eval.device)
indices = np.arange(self.batch_size)
V_s, A_s = self.q_eval.forward(states)
V_s_, A_s_ = self.q_next.forward(states_)
V_s_eval, A_s_eval = self.q_eval.forward(states_)
q_pred = T.add(V_s,
(A_s - A_s.mean(dim=1, keepdim=True)))[indices, actions]
q_next = T.add(V_s_,
(A_s_ - A_s_.mean(dim=1, keepdim=True)))
q_eval = T.add(V_s_eval, (A_s_eval - A_s_eval.mean(dim=1,keepdim=True)))
max_actions = T.argmax(q_eval, dim=1)
q_next[dones] = 0.0
q_target = rewards + self.gamma*q_next[indices, max_actions]
loss = self.q_eval.loss(q_target, q_pred).to(self.q_eval.device)
loss.backward()
self.q_eval.optimizer.step()
self.q_next.optimizer.step()
self.learn_step_counter += 1
self.decrement_epsilon()