我担心将 Cartpole 代码理解为深度 Q 学习的示例。DQL代理部分代码如下:
class DQLAgent:
def __init__(self, env):
# parameter / hyperparameter
self.state_size = env.observation_space.shape[0]
self.action_size = env.action_space.n
self.gamma = 0.95
self.learning_rate = 0.001
self.epsilon = 1 # explore
self.epsilon_decay = 0.995
self.epsilon_min = 0.01
self.memory = deque(maxlen = 1000)
self.model = self.build_model()
def build_model(self):
# neural network for deep q learning
model = Sequential()
model.add(Dense(48, input_dim = self.state_size, activation = "tanh"))
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):
# storage
self.memory.append((state, action, reward, next_state, done))
def act(self, state):
# acting: explore or exploit
if random.uniform(0,1) <= self.epsilon:
return env.action_space.sample()
else:
act_values = self.model.predict(state)
return np.argmax(act_values[0])
def replay(self, batch_size):
# training
if len(self.memory) < batch_size:
return
minibatch = random.sample(self.memory,batch_size)
for state, action, reward, next_state, done in minibatch:
if done:
target = reward
else:
target = reward + self.gamma*np.amax(self.model.predict(next_state)[0])
train_target = self.model.predict(state)
train_target[0][action] = target
self.model.fit(state,train_target, verbose = 0)
def adaptiveEGreedy(self):
if self.epsilon > self.epsilon_min:
self.epsilon *= self.epsilon_decay
在训练部分,我们找到了我们的目标和train_target。那么我们为什么设置train_target[0][action] = target
在这里呢?
学习时做出的每一个预测都是不正确的,但是由于误差计算和反向传播,在网络末端做出的预测会越来越接近,但是当我们在train_target[0][action] = target
这里做的时候,误差就变成了0,在这种情况下,学习是?