分类： Python/Ruby
2022-07-19 17:02:21
import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.nn.functional as F
import torch.optim as optim
import torchvision.transforms as T
from torch import FloatTensor, LongTensor, ByteTensor
from collections import namedtuple
import random
Tensor = FloatTensor
EPSILON = 0 # epsilon used for epsilon greedy approach
GAMMA = 0.9
TARGET_NETWORK_REPLACE_FREQ = 40 # How frequently target netowrk updates
MEMORY_CAPACITY = 100
BATCH_SIZE = 80
LR = 0.01 # learning rate
class DQNNet(nn.Module):
def __init__(self):
super(DQNNet,self).__init__()
self.linear1 = nn.Linear(35,35)
self.linear2 = nn.Linear(35,5)
def forward(self,s):
s=torch.FloatTensor(s)
s = s.view(s.size(0),1,35)
s = self.linear1(s)
s = self.linear2(s)
return s
class DQN(object):
def __init__(self):
self.net,self.target_net = DQNNet(),DQNNet()
self.learn_step_counter = 0
self.memory = []
self.position = 0
self.capacity = MEMORY_CAPACITY
self.optimizer = torch.optim.Adam(self.net.parameters(), lr=LR)
self.loss_func = 外汇跟单gendan5.comnn.MSELoss()
def choose_action(self,s,e):
x=np.expand_dims(s, axis=0)
if np.random.uniform() < 1-e:
actions_value = self.net.forward(x)
action = torch.max(actions_value,-1)[1].data.numpy()
action = action.max()
else:
action = np.random.randint(0, 5)
return action
def push_memory(self, s, a, r, s_):
if len(self.memory) < self.capacity:
self.memory.append(None)
self.memory[self.position] = Transition(torch.unsqueeze(torch.FloatTensor(s), 0),torch.unsqueeze(torch.FloatTensor(s_), 0),\
torch.from_numpy(np.array([a])),torch.from_numpy(np.array([r],dtype='float32')))#
self.position = (self.position + 1) % self.capacity
def get_sample(self,batch_size):
sample = random.sample(self.memory,batch_size)
return sample
def learn(self):
if self.learn_step_counter % TARGET_NETWORK_REPLACE_FREQ == 0:
self.target_net.load_state_dict(self.net.state_dict())
self.learn_step_counter += 1
transitions = self.get_sample(BATCH_SIZE)
batch = Transition(*zip(*transitions))
b_s = Variable(torch.cat(batch.state))
b_s_ = Variable(torch.cat(batch.next_state))
b_a = Variable(torch.cat(batch.action))
b_r = Variable(torch.cat(batch.reward))
q_eval = self.net.forward(b_s).squeeze(1).gather(1,b_a.unsqueeze(1).to(torch.int64))
q_next = self.target_net.forward(b_s_).detach() #
q_target = b_r + GAMMA * q_next.squeeze(1).max(1)[0].view(BATCH_SIZE, 1).t()
loss = self.loss_func(q_eval, q_target.t())
self.optimizer.zero_grad() # reset the gradient to zero
loss.backward()
self.optimizer.step() # execute back propagation for one step
return loss
Transition = namedtuple('Transition',('state', 'next_state','action', 'reward'))
