对输入的重构通过编码器和解码器完成。例如:
obs —encoder—> state presentation —decoder—> obs_reconstruction
根据既有网络层（编码器）构建解码器时，根据编码器的变量shape确定对应的解码器output_shape. For example:
# encoder
conv1 = layers.conv2d(
num_filters=32, filter_size=8, stride=4, padding=1, act='relu')
conv2 = layers.conv2d(
num_filters=64, filter_size=4, stride=2, padding=2, act='relu')
conv3 = layers.conv2d(
num_filters=64, filter_size=3, stride=1, padding=0, act='relu')
fc = layers.fc(size=512, act='relu')
# normally, we flatten input before **fc**, and reshape before **defc**
# decoder
defc = layers.fc(size=5184, act='relu')
deconv3 = layers.conv2d_transpose(
num_filters=64, filter_size=3, stride=1, padding=0, act='relu')
deconv2 = layers.conv2d_transpose(
num_filters=32, filter_size=4, stride=2, padding=2, act='relu')
deconv1 = layers.conv2d_transpose(
num_filters=4, filter_size=8, stride=4, padding=0, act='relu')
参数详情可参考https://www.paddlepaddle.org.cn/documentation/docs/zh/api_cn/dygraph_cn.html#conv2dtranspose
