为什么我的网络返回一个大于输出空间长度的整数

Question

我正在学习Deep-Q-Network，并尝试在 https://github.com/keon/deep-q-learning/blob/master/dqn.py 更改代码以尝试atari breakout。 但是我的网络的输出有时大于输出空间。 原作者的代码没有问题，但是更改代码后，就出现了问题。

我在Windows 10上运行python 3.7，使用Numpy，keras-gpu，并在AMD Ryzen 3700x和rtx 2070 super上运行。 我以为这是一个神经网络模型问题，但我什么也做不了，因为我不知道如何解决它。

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(Conv2D(32, kernel_size=(5, 5), input_shape=(105, 80, 1), 
activation='relu'))
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)
state = np.expand_dims(state, 3)
state = np.expand_dims(state, 0)
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:
next_state = np.expand_dims(next_state, 3)
next_state = np.expand_dims(next_state, 0)
state = np.expand_dims(state, 3)
state = np.expand_dims(state, 0)
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

期望 act(( 的输出 0 ~ 3，但有时 act(( 返回超过 2000。

Answer 1

神经网络的输出大小取决于...

self.action_space = action_space

。行在初始化(...(。初始化代理时，您在第二个参数中传递了什么？这就是您设置为神经网络的输出大小。