Hello.
I’m trying to make an ai for bitcoin trade where it receives as status 5 days with price Close, Open, High, Low, macd and rsi. with buy, sell or hold action.
code: Google Colab
But I don’t know exactly how to build the code and it’s showing the error:
ValueError Traceback (most recent call last)
in <cell line: 6>()
12
13 experience, unused_info = next(iterator)
—> 14 train_loss = agent.train(experience).loss
15
16
5 frames
/usr/local/lib/python3.9/dist-packages/tf_agents/agents/data_converter.py in _validate_trajectory(value, trajectory_spec, sequence_length, num_outer_dims)
183 else ‘one outer dimension’)
184 shape_prefix_str = ‘[B, T]’ if num_outer_dims == 2 else ‘[B]’
→ 185 raise ValueError(
186 'All of the Tensors in value must have {shape_str}. Specifically, ’
187 ‘tensors must have shape {shape_prefix_str} + spec.shape.\n’
ValueError: All of the Tensors in value must have two outer dimensions. Specifically, tensors must have shape [B, T] + spec.shape.
Full shapes of value tensors:
Trajectory(
{‘action’: TensorShape([]),
‘discount’: TensorShape([]),
‘next_step_type’: TensorShape([]),
‘observation’: TensorShape([5, 10]),
‘policy_info’: (),
‘reward’: TensorShape([]),
‘step_type’: TensorShape([])}).
Expected shapes (excluding the two outer dimensions):
Trajectory(
{‘action’: TensorShape([]),
‘discount’: TensorShape([]),
‘next_step_type’: TensorShape([]),
‘observation’: TensorShape([5, 10]),
‘policy_info’: (),
‘reward’: TensorShape([]),
‘step_type’: TensorShape([])}).