我是在经过时间顺序还是向量？

Question

我试图将三个元素的列表作为时间序列传递给嵌入，然后传递给LSTM，但我真的不知道是否只传递一个向量为3的值。下面是代码：

lr = 1e-3
emb_size = 100
look_back = 3

# "Expert" (regular dqn) model architecture

inp = Input(shape=(look_back,))
emb = Embedding(input_dim=env.action_space.n+1, output_dim = emb_size)(inp) 
rnn = Bidirectional(LSTM(5))(emb)
out = Dense(env.action_space.n, activation='softmax')(rnn)
expert_model = Model(inputs = inp, outputs = out)
expert_model.compile(loss='categorical_crossentropy', optimizer= Adam(lr))

print(expert_model.summary())

以下是总结：

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         (None, 3)                 0         
_________________________________________________________________
embedding_1 (Embedding)      (None, 3, 100)            1100      
_________________________________________________________________
bidirectional_1 (Bidirection (None, 10)                4240      
_________________________________________________________________
dense_1 (Dense)              (None, 10)                110       
=================================================================
Total params: 5,450
Trainable params: 5,450
Non-trainable params: 0
_________________________________________________________________