Error when I learn with a demo

Hello/ I get an error when I try to teach my bot using demontration. What does that mean?

ValueError: Cannot feed value of shape (128, 4) for Tensor 'Placeholder_2:0', which has shape '(?, 3)'

 

I recorded the demonstration through the component DemonstrationRecorder
Agent have 5 observation and 3 stacked vector
Discrete Branche 3 [3,3,3]
The demo file is in the project folder.
in yaml rwite like pyramids ex.:
extrinsic:
strength: 2.0
gamma: 0.99
gail:
strength: 0.02
gamma: 0.99
encoding_size: 128
use_actions: true
demo_path: W:/UnityProjects/FamProject_AI/Assets/World/Demos/FamSurvDemo.demo

 

And 2 Per. Ray

 

Agent have two 3D Ray Perception Sensors

 

No, I recorded a new

 

Version information:
ml-agents: 0.15.0,
ml-agents-envs: 0.15.0,
Communicator API: 0.15.0,
TensorFlow: 2.0.1

I've already changed everything. But I still can’t use the demo. Now another error:

TypeError: float() argument must be a string or a number, not 'google.protobuf.pyext._message.RepeatedScalarContainer'

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "C:\Users\Lex\AppData\Local\Programs\Python\Python37\lib\runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "C:\Users\Lex\AppData\Local\Programs\Python\Python37\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "C:\Users\Lex\python-envs\sample-env\Scripts\mlagents-learn.exe\__main__.py", line 7, in <module>
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents\trainers\learn.py", line 495, in main
run_cli(parse_command_line())
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents\trainers\learn.py", line 491, in run_cli
run_training(run_seed, options)
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents\trainers\learn.py", line 329, in run_training
tc.start_learning(env_manager)
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents_envs\timers.py", line 258, in wrapped
return func(*args, **kwargs)
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents\trainers\trainer_controller.py", line 205, in start_learning
self._create_trainers_and_managers(env_manager, new_behavior_ids)
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents\trainers\trainer_controller.py", line 191, in _create_trainers_and_managers
self._create_trainer_and_manager(env_manager, behavior_id)
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents\trainers\trainer_controller.py", line 172, in _create_trainer_and_manager
trainer.add_policy(name_behavior_id, policy)
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents\trainers\sac\trainer.py", line 358, in add_policy
self.optimizer = SACOptimizer(self.policy, self.trainer_parameters)
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents\trainers\sac\optimizer.py", line 46, in __init__
super().__init__(policy, trainer_params)
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents\trainers\optimizer\tf_optimizer.py", line 21, in __init__
self.create_reward_signals(trainer_params["reward_signals"])
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents\trainers\optimizer\tf_optimizer.py", line 134, in create_reward_signals
self.policy, reward_signal, config
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents\trainers\components\reward_signals\reward_signal_factory.py", line 36, in create_reward_signal
class_inst = rcls(policy, **config_entry)
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents\trainers\components\reward_signals\gail\signal.py", line 44, in __init__
_, self.demonstration_buffer = demo_to_buffer(demo_path, policy.sequence_length)
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents_envs\timers.py", line 258, in wrapped
return func(*args, **kwargs)
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents\trainers\demo_loader.py", line 85, in demo_to_buffer
demo_buffer = make_demo_buffer(info_action_pair, group_spec, sequence_length)
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents_envs\timers.py", line 258, in wrapped
return func(*args, **kwargs)
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents\trainers\demo_loader.py", line 65, in make_demo_buffer
demo_processed_buffer, batch_size=None, training_length=sequence_length
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents\trainers\buffer.py", line 283, in resequence_and_append
batch_size=batch_size, training_length=training_length
File "c:\users\lex\python-envs\sample-env\lib\site-packages\mlagents\trainers\buffer.py", line 106, in get_batch
dtype=np.float32,
ValueError: setting an array element with a sequence.