这是DQN的主要代码，唯一的区别是我的状态有5个变量来代替一个state=[var1 var2 var3 var4 var5]，我需要向状态添加内存，我的意思是state[i]被替换为
state[i-k+1]...state[i]
为此需要进行哪些必要的更改？我建立模型，我将输入数乘以k，但我不知道在哪里调用该函数（build_model）？因为我看到
的错误 agent.replay(batch_size)
File "modgame.py", , in replay
np.argmax(self.model.predict(next_state)[0])
File "C:\Users\L\Anaconda30\envs\tensorflow\lib\site-packages\keras\models.py", line 1064, in predict
steps=steps)
File "C:\Users\L\Anaconda30\envs\tensorflow\lib\site-packages\keras\engine\training.py", line 1817, in predict
check_batch_axis=False)
File "C:\Users\L\Anaconda30\envs\tensorflow\lib\site-packages\keras\engine\training.py", line 123, in _standardize_input_data
str(data_shape))
ValueError: Error when checking : expected dense_1_input to have shape (30,) but got array with shape (5,)
我进行了一些更改，但还不够！每个状态也是我的代码中的5和k=6的组合，因此我应该输入5*6，但这仅仅是5！
# -*- coding: utf-8 -*-
import random
import gym
import numpy as np
from collections import deque
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import Adam
EPISODES = 1000
class DQNAgent:
def __init__(self, state_size, action_size):
self.state_size = state_size
self.action_size = action_size
self.memory = deque(maxlen=2000)
self.gamma = 0.95 # discount rate
self.epsilon = 1.0 # exploration rate
self.epsilon_min = 0.01
self.epsilon_decay = 0.995
self.learning_rate = 0.001
self.model = self._build_model()
def _build_model(self):
# Neural Net for Deep-Q learning Model
model = Sequential()
model.add(Dense(24, input_dim=self.state_size, activation='relu'))
model.add(Dense(24, activation='relu'))
model.add(Dense(self.action_size, activation='linear'))
model.compile(loss='mse',
optimizer=Adam(lr=self.learning_rate))
return model
def remember(self, state, action, reward, next_state, done):
self.memory.append((state, action, reward, next_state, done))
def act(self, state):
if np.random.rand() <= self.epsilon:
return random.randrange(self.action_size)
act_values = self.model.predict(state)
return np.argmax(act_values[0]) # returns action
def replay(self, batch_size):
minibatch = random.sample(self.memory, batch_size)
for state, action, reward, next_state, done in minibatch:
target = reward
if not done:
target = (reward + self.gamma *
np.amax(self.model.predict(next_state)[0]))
target_f = self.model.predict(state)
target_f[0][action] = target
self.model.fit(state, target_f, epochs=1, verbose=0)
if self.epsilon > self.epsilon_min:
self.epsilon *= self.epsilon_decay
def load(self, name):
self.model.load_weights(name)
def save(self, name):
self.model.save_weights(name)
if __name__ == "__main__":
env = gym.make('CartPole-v1')
state_size = env.observation_space.shape[0]
action_size = env.action_space.n
agent = DQNAgent(state_size, action_size)
# agent.load("./save/cartpole-dqn.h5")
done = False
batch_size = 32
for e in range(EPISODES):
state = env.reset()
state = np.reshape(state, [1, state_size])
for time in range(500):
# env.render()
action = agent.act(state)
next_state, reward, done, _ = env.step(action)
reward = reward if not done else -10
next_state = np.reshape(next_state, [1, state_size])
agent.remember(state, action, reward, next_state, done)
state = next_state
if done:
print("episode: {}/{}, score: {}, e: {:.2}"
.format(e, EPISODES, time, agent.epsilon))
break
if len(agent.memory) > batch_size:
agent.replay(batch_size)
# if e % 10 == 0:
# agent.save("./save/cartpole-dqn.h5")