我一直在尝试使用RLLib建立自定义LSTM模型,但是由于某些原因,在尝试训练时,我的LSTM层出现了形状不兼容的错误。特别是,此错误似乎与批次大小有关,因为针对不兼容形状列出的尺寸随我的批次大小值线性变化。我的模型代码如下:
class CustomLSTMModel(RecurrentNetwork):
"""Example of using the Keras functional API to define a RNN model."""
def __init__(
self,
obs_space,
action_space,
num_outputs,
model_config,
name,
hiddens_size=64,
cell_size=64,
):
super(CustomLSTMModel, self).__init__(
obs_space, action_space, num_outputs, model_config, name
)
self.cell_size = cell_size
# Define input layers
input_layer = tf.keras.layers.Input(
shape=(obs_space.shape[0], obs_space.shape[1]), name="inputs"
)
state_in_h = tf.keras.layers.Input(shape=(cell_size,), name="h")
state_in_c = tf.keras.layers.Input(shape=(cell_size,), name="c")
# FC layer
dense1 = tf.keras.layers.Dense(hiddens_size, name="dense_1")(input_layer)
# LSTM layer
lstm_1_out, state_1_h, state_1_c = tf.keras.layers.LSTM(
cell_size,
return_state=True,
name="lstm_1",
)(
inputs=dense1,
initial_state=[state_in_h, state_in_c],
)
# Postprocess
logits = tf.keras.layers.Dense(
self.num_outputs,
activation=None,
name="logits",
)(lstm_1_out)
values = tf.keras.layers.Dense(
1,
activation=None,
name="values",
)(lstm_1_out)
# Create the RNN model
self.rnn_model = tf.keras.Model(
inputs=[input_layer, state_in_h, state_in_c],
outputs=[logits, values, state_1_h, state_1_c],
)
self.register_variables(self.rnn_model.variables)
self.rnn_model.summary()
@override(ModelV2)
def forward(self, input_dict, state, seq_lens):
"""Custom forward pass for inputs that already have time dimension."""
inputs = input_dict["obs"]
output, new_state = self.forward_rnn(inputs, state, seq_lens)
return tf.reshape(output, [-1, self.num_outputs]), new_state
@override(RecurrentNetwork)
def forward_rnn(self, inputs, state, seq_lens):
model_out, self._value_out, h, c = self.rnn_model([inputs] + state)
return model_out, [h, c]
@override(ModelV2)
def get_initial_state(self):
return [
np.zeros(self.cell_size, np.float32),
np.zeros(self.cell_size, np.float32),
]
@override(ModelV2)
def value_function(self):
return tf.reshape(self._value_out, [-1])
这非常接近于现有的RNN模型的RLLib代码,位于以下位置:https://github.com/ray-project/ray/blob/8abe13023f72dabeb233278c0b7b4f80f84c5cc3/rllib/models/tf/recurrent_net.py
我必须进行的主要更改是在覆盖的前向传递函数中,因为作为该函数的输入提供的input_dict已经添加了时间维度,因此进入的维度为(?,5, 50)(?,10、50)等。因此,我不需要它们用于添加新时间维度的add_time_dimension函数。我认为的另一个重要变化是如何在模型类中定义输入层的形状。实际上,我得到的错误基本上与此相同,只是形状不匹配的值不同:Dimensions error, in seq2seq model (op: 'Add') with input shapes: [512,64], [5739,64]
任何想法将不胜感激!