小编dro*_*ngo的帖子

我想知道为什么这个功能：

@tf.function
def train(self,TargetNet,epsilon):
    if len(self.experience['s']) < self.min_experiences:
        return 0
    ids=np.random.randint(low=0,high=len(self.replay_buffer['s']),size=self.batch_size)
    states=np.asarray([self.experience['s'][i] for i in ids])
    actions=np.asarray([self.experience['a'][i] for i in ids])
    rewards=np.asarray([self.experience['r'][i] for i in ids])
    next_states=np.asarray([self.experience['s1'][i] for i in ids])
    dones = np.asarray([self.experience['done'][i] for i in ids])
    q_next_actions=self.get_action(next_states,epsilon)
    q_value_next=TargetNet.predict(next_states)
    q_value_next=tf.gather_nd(q_value_next,tf.stack((tf.range(self.batch_size),q_next_actions),axis=1))
    targets=tf.where(dones, rewards, rewards+self.gamma*q_value_next)

    with tf.GradientTape() as tape:
        estimates=tf.math.reduce_sum(self.predict(states)*tf.one_hot(actions,self.num_actions),axis=1)
        loss=tf.math.reduce_sum(tf.square(estimates - targets))
    variables=self.model.trainable_variables
    gradients=tape.gradient(loss,variables)
    self.optimizer.apply_gradients(zip(gradients,variables))

给出 ValueError：在非第一次调用用 tf.function 修饰的函数时创建变量。而这段代码非常相似：

@tf.function
def train(self, TargetNet):
    if len(self.experience['s']) < self.min_experiences:
        return 0
    ids = np.random.randint(low=0, high=len(self.experience['s']), size=self.batch_size)
    states = np.asarray([self.experience['s'][i] for i in …