https://blog.csdn.net/qq_36499794/article/details/103162841
import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
import gym
# 定义参数
BATCH_SIZE = 32 # 每一批的训练量
LR = 0.01 # 学习率
EPSILON = 0.9 # 贪婪策略指数,Q-learning的一个指数,用于指示是探索还是利用。
GAMMA = 0.9 # reward discount
TARGET_REPLACE_ITER = 100 # target的更新频率
MEMORY_CAPACITY = 2000
env = gym.make('CartPole-v0')
env = env.unwrapped
N_ACTIONS = env.action_space.n
N_STATES = env.observation_space.shape[0]
ENV_A_SHAPE = 0 if isinstance(env.action_space.sample(), int) else env.action_space.sample().shape # to confirm the shape
# 创建神经网络模型,输出的是可能的动作
class Net(nn.Module):
def __init__(self, ):
super(Net, self).__init__()
self.fc1 = nn.Linear(N_STATES, 50)
self.fc1.weight.data.normal_(0, 0.1) # initialization
self.out = nn.Linear(50, N_ACTIONS)
self.out.weight.data.normal_(0, 0.1) # initialization
def forward(self, x):
x = self.fc1(x)
x = F.relu(x)
actions_value = self.out(x)
return actions_value
# 创建Q-learning的模型
class DQN(object):
def __init__(self):
# 两张网是一样的,不过就是target_net是每100次更新一次,eval_net每次都更新
self.eval_net, self.target_net = Net(), Net()
self.learn_step_counter = 0 # 如果次数到了,更新target_net
self.memory_counter = 0 # for storing memory
self.memory = np.zeros((MEMORY_CAPACITY, N_STATES * 2 + 2)) # 初始化记忆
self.optimizer = torch.optim.Adam(self.eval_net.parameters(), lr=LR)
self.loss_func = nn.MSELoss()
# 选择动作
def choose_action(self, x):
x = torch.unsqueeze(torch.FloatTensor(x), 0)
# input only one sample
if np.random.uniform() < EPSILON: # 贪婪策略
actions_value = self.eval_net.forward(x)
action = torch.max(actions_value, 1)[1].data.numpy()
action = action[0] if ENV_A_SHAPE == 0 else action.reshape(ENV_A_SHAPE) # return the argmax index
else: # random
action = np.random.randint(0, N_ACTIONS)
action = action if ENV_A_SHAPE == 0 else action.reshape(ENV_A_SHAPE)
return action
# 存储记忆
def store_transition(self, s, a, r, s_):
transition = np.hstack((s, [a, r], s_)) # 将每个参数打包起来
# replace the old memory with new memory
index = self.memory_counter % MEMORY_CAPACITY
self.memory[index, :] = transition
self.memory_counter += 1
def learn(self):
# target parameter update
if self.learn_step_counter % TARGET_REPLACE_ITER == 0:
self.target_net.load_state_dict(self.eval_net.state_dict())
self.learn_step_counter += 1
# 学习过程
sample_index = np.random.choice(MEMORY_CAPACITY, BATCH_SIZE)
b_memory = self.memory[sample_index, :]
b_s = torch.FloatTensor(b_memory[:, :N_STATES])
b_a = torch.LongTensor(b_memory[:, N_STATES:N_STATES+1].astype(int))
b_r = torch.FloatTensor(b_memory[:, N_STATES+1:N_STATES+2])
b_s_ = torch.FloatTensor(b_memory[:, -N_STATES:])
# q_eval w.r.t the action in experience
q_eval = self.eval_net(b_s).gather(1, b_a) # shape (batch, 1)
q_next = self.target_net(b_s_).detach() # detach的作用就是不反向传播去更新,因为target的更新在前面定义好了的
q_target = b_r + GAMMA * q_next.max(1)[0].view(BATCH_SIZE, 1) # shape (batch, 1)
loss = self.loss_func(q_eval, q_target)
self.optimizer.zero_grad()
loss.backward()
self.optimizer.step()
dqn = DQN()
print('\nCollecting experience...')
for i_episode in range(400):
s = env.reset() # 搜集当前环境状态。
ep_r = 0
while True:
env.render()
a = dqn.choose_action(s)
# take action
s_, r, done, info = env.step(a)
# modify the reward
x, x_dot, theta, theta_dot = s_
r1 = (env.x_threshold - abs(x)) / env.x_threshold - 0.8
r2 = (env.theta_threshold_radians - abs(theta)) / env.theta_threshold_radians - 0.5
r = r1 + r2
dqn.store_transition(s, a, r, s_)
ep_r += r
if dqn.memory_counter > MEMORY_CAPACITY:
dqn.learn()
if done:
print('Ep: ', i_episode,
'| Ep_r: ', round(ep_r, 2))
if done:
break
s = s_