-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathDDPG.py
146 lines (115 loc) · 5.69 KB
/
DDPG.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
import os
import numpy as np
import torch as T
import torch.nn.functional as F
from networks import ActorNetwork, CriticNetwork
from noise import OUActionNoise
from buffer import ReplayBuffer
class Agent():
def __init__(self, alpha, beta, input_dims, tau, n_actions, gamma,
max_size, C_fc1_dims, C_fc2_dims, C_fc3_dims, A_fc1_dims, A_fc2_dims, batch_size, n_agents):
self.gamma = gamma
self.tau = tau
self.batch_size = batch_size
self.alpha = alpha
self.beta = beta
self.number_agents = n_agents
self.number_actions = n_actions
self.memory = ReplayBuffer(max_size, input_dims, n_actions, n_agents)
self.noise = OUActionNoise(mu=np.zeros(n_actions*n_agents))
self.actor = ActorNetwork(alpha, input_dims, A_fc1_dims, A_fc2_dims, n_agents,
n_actions=n_actions, name='actor')
self.critic = CriticNetwork(beta, input_dims, C_fc1_dims, C_fc2_dims, C_fc3_dims, n_agents,
n_actions=n_actions, name='critic')
self.target_actor = ActorNetwork(alpha, input_dims, A_fc1_dims, A_fc2_dims, n_agents,
n_actions=n_actions, name='target_actor')
self.target_critic = CriticNetwork(beta, input_dims, C_fc1_dims, C_fc2_dims, C_fc3_dims, n_agents,
n_actions=n_actions, name='target_critic')
self.update_network_parameters(tau=1)
def choose_action(self, observation):
self.actor.eval()
#state = T.tensor([observation], dtype=T.float).to(self.actor.device)
state = T.tensor([np.array(observation)], dtype=T.float).to(self.actor.device)
mu = self.actor.forward(state).to(self.actor.device)
#print('check this variable for convergence!!! : ', mu)
mu_prime = mu #+ T.tensor(self.noise(), dtype=T.float).to(self.actor.device)
self.actor.train()
return mu_prime.cpu().detach().numpy()[0]
def remember(self, state, action, reward, state_, done):
self.memory.store_transition(state, action, reward, state_, done)
def save_models(self):
self.actor.save_checkpoint()
self.target_actor.save_checkpoint()
self.critic.save_checkpoint()
self.target_critic.save_checkpoint()
def load_models(self):
self.actor.load_checkpoint()
self.target_actor.load_checkpoint()
self.critic.load_checkpoint()
self.target_critic.load_checkpoint()
def learn(self):
if self.memory.mem_cntr < self.batch_size:
return
states, actions, rewards, states_, done = \
self.memory.sample_buffer(self.batch_size)
states = T.tensor(states, dtype=T.float).to(self.actor.device)
states_ = T.tensor(states_, dtype=T.float).to(self.actor.device)
actions = T.tensor(actions, dtype=T.float).to(self.actor.device)
rewards = T.tensor(rewards, dtype=T.float).to(self.actor.device)
done = T.tensor(done).to(self.actor.device)
self.target_actor.eval()
self.target_critic.eval()
self.critic.eval()
target_actions = self.target_actor.forward(states_)
critic_value_ = self.target_critic.forward(states_, target_actions)
critic_value = self.critic.forward(states, actions)
critic_value_[done] = 0.0
critic_value_ = critic_value_.view(-1)
target = rewards + self.gamma * critic_value_
target = target.view(self.batch_size, 1)
self.critic.train()
self.critic.optimizer.zero_grad()
critic_loss = F.mse_loss(target, critic_value)
critic_loss.backward()
self.critic.optimizer.step()
self.critic.eval()
self.actor.train()
self.actor.optimizer.zero_grad()
actor_loss = -self.critic.forward(states, self.actor.forward(states))
actor_loss = T.mean(actor_loss)
actor_loss.backward()
self.actor.optimizer.step()
self.update_network_parameters()
def update_network_parameters(self, tau=None):
if tau is None:
tau = self.tau
actor_params = self.actor.named_parameters()
critic_params = self.critic.named_parameters()
target_actor_params = self.target_actor.named_parameters()
target_critic_params = self.target_critic.named_parameters()
critic_state_dict = dict(critic_params)
actor_state_dict = dict(actor_params)
target_critic_state_dict = dict(target_critic_params)
target_actor_state_dict = dict(target_actor_params)
for name in critic_state_dict:
critic_state_dict[name] = tau * critic_state_dict[name].clone() + \
(1 - tau) * target_critic_state_dict[name].clone()
for name in actor_state_dict:
actor_state_dict[name] = tau * actor_state_dict[name].clone() + \
(1 - tau) * target_actor_state_dict[name].clone()
self.target_critic.load_state_dict(critic_state_dict)
self.target_actor.load_state_dict(actor_state_dict)
"""
#Verify that the copy assignment worked correctly
target_actor_params = self.target_actor.named_parameters()
target_critic_params = self.target_critic.named_parameters()
critic_state_dict = dict(target_critic_params)
actor_state_dict = dict(target_actor_params)
print('\nActor Networks', tau)
for name, param in self.actor.named_parameters():
print(name, T.equal(param, actor_state_dict[name]))
print('\nCritic Networks', tau)
for name, param in self.critic.named_parameters():
print(name, T.equal(param, critic_state_dict[name]))
input()
"""