Problem with action_encoder

[albert88as]

Hi Haryoa,
Im learning about reinforcement learning and very interested to your project. But i cant run this project in my computer. This faces with enconde error that

2021-04-11 16:22:22.072479: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)to use the following CPU instructions in performance-critical operations:  AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
D:\ana3\envs\cudatk\lib\site-packages\sklearn\utils\validation.py:70: FutureWarning: Pass categories=2998 as keyword args. From version 1.0 (renaming of 0.25) passing these as positional arguments will result in an error
  warnings.warn(f"Pass {args_msg} as keyword args. From version "
list_all_action 
 [[   0]
 [2674]
 [2676]
 ...
 [2646]
 [2665]
 [2997]]
Traceback (most recent call last):
  File "main.py", line 118, in <module>
    main_alpha_zero_train()
  File "main.py", line 41, in main_alpha_zero_train
    ae.fit(list_all_action=all_action_spaces)
  File "D:\88Projects\AlphaZero\evo-pawness\reinforcement_learning_train\util\action_encoder.py", line 29, in fit
    self.onehot_encoder.fit(list_all_action)
  File "D:\ana3\envs\cudatk\lib\site-packages\sklearn\preprocessing\_encoders.py", line 417, in fit
    self._fit(X, handle_unknown=self.handle_unknown,
  File "D:\ana3\envs\cudatk\lib\site-packages\sklearn\preprocessing\_encoders.py", line 81, in _fit
    if len(self.categories) != n_features:
TypeError: object of type 'int' has no len()

can you help me to solve this problem.
Thank you!
Albert