运用动态图的DDPG代码model部分报错ValueError: (InvalidArgument) The shape of input[0] and input[1] is expected to be equal.But received input[0]'s shape = [48, 8], input[1]'s shape = [48, 1, 2].

[lzlbit123]

版本都在PARL/examples/tutorials/lesson5/ddpg
/model.py 这里，代码也在这里借鉴的，但是运行的时候（不是在carpole环境中，是一个定义的act_dim=2,obs_dim=8的一个环境）
报错：Traceback (most recent call last):
File "C:\Users\lzlbi\PycharmProjects\PPO\train1.py", line 100, in
main()
File "C:\Users\lzlbi\PycharmProjects\PPO\train1.py", line 86, in main
run_train_episode(agent, env, rpm)
File "C:\Users\lzlbi\PycharmProjects\PPO\train1.py", line 38, in run_train_episode
batch_done)
File "C:\Users\lzlbi\PycharmProjects\PPO\agent1.py", line 46, in learn
terminal)
File "C:\Users\lzlbi\PycharmProjects\PPO\alg1.py", line 50, in learn
terminal)
File "C:\Users\lzlbi\PycharmProjects\PPO\alg1.py", line 65, in _critic_learn
current_Q = self.model.value(obs, action)
File "C:\Users\lzlbi\PycharmProjects\PPO\model1.py", line 17, in value
return self.critic_model(obs, action)
File "D:\anaconda\envs\paddle\lib\site-packages\paddle\fluid\dygraph\layers.py", line 914, in call
outputs = self.forward(*inputs, **kwargs)
File "C:\Users\lzlbi\PycharmProjects\PPO\model1.py", line 49, in forward
concat = paddle.concat([obs, act], axis=1)
File "D:\anaconda\envs\paddle\lib\site-packages\paddle\tensor\manipulation.py", line 345, in concat
return paddle.fluid.layers.concat(input=x, axis=axis, name=name)
File "D:\anaconda\envs\paddle\lib\site-packages\paddle\fluid\layers\tensor.py", line 327, in concat
return _C_ops.concat(input, 'axis', axis)
ValueError: (InvalidArgument) The shape of input[0] and input[1] is expected to be equal.But received input[0]'s shape = [48, 8], input[1]'s shape = [48, 1, 2].
[Hint: Expected inputs_dims[i].size() == out_dims.size(), but received inputs_dims[i].size():3 != out_dims.size():2.] (at C:\home\workspace\Paddle_release\paddle/fluid/operators/concat_op.h:40)
[operator < concat > error]
请问是怎么回事呢，看了网上很多例子都是代码差不多的，不知道哪里有问题，如何修改呢？