我正在使用 DQN 进行资源分配,代理应将到达请求分配给最佳虚拟机。我正在修改 Cartpole 代码如下:
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
import os
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
self.epsilon = 1.0
self.epsilon_decay = 0.995
self.epsilon_min = 0.01
self.learning_rate = 0.001
self.model = self._build_model()
def _build_model(self):
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])
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)
Cartpole 状态作为 Q 网络的输入是由环境给定的。
0 Cart Position
1 Cart Velocity -Inf Inf
2 Pole Angle ~ -41.8° ~ 41.8°
3 Pole Velocity At Tip
问题是在我的代码中 Q 网络的输入是什么?因为代理应该根据到达请求的大小采取最好的行动,但这不是由环境给出的。我应该通过这个输入值,大小来输入 Q 网络吗?