Getting unexpected keyword error in CatBoostRegressor while using GridSearchCV

I am trying to use GridSearchCV on a CatBoostRegressor algorithm, but get some "unexpected keyword" errors on 3 different params (classes_count, auto_class_weights, and bayesian_matrix_reg) when using these params in the grid. I got the list of params from the algorithm itself, after calling fit(), so these params should exist.

I double checked with the website, and can find the first 2 in the documentation, but can’t find the bayesian_matrix_reg parameter. Not sure where this came from, but the model is using it.

I am currently commenting out these 3 params, but would like to avoid having to manually remove these parameters that exist, but still give unexpected keyword errors when testing.

I am using catboost 0.23.2

My code:

CBoost = CatBoostRegressor(logging_level='Silent')
CBoost.fit(train, y_train)
CBoost.get_all_params()

{'nan_mode': 'Min',
 'eval_metric': 'RMSE',
 'iterations': 1000,
 'sampling_frequency': 'PerTree',
 'leaf_estimation_method': 'Newton',
 'grow_policy': 'SymmetricTree',
 'penalties_coefficient': 1,
 'boosting_type': 'Plain',
 'model_shrink_mode': 'Constant',
 'feature_border_type': 'GreedyLogSum',
 'bayesian_matrix_reg': 0.10000000149011612,
 'l2_leaf_reg': 3,
 'random_strength': 1,
 'rsm': 1,
 'boost_from_average': True,
 'model_size_reg': 0.5,
 'subsample': 0.800000011920929,
 'use_best_model': False,
 'random_seed': 0,
 'depth': 6,
 'border_count': 254,
 'classes_count': 0,
 'auto_class_weights': 'None',
 'sparse_features_conflict_fraction': 0,
 'leaf_estimation_backtracking': 'AnyImprovement',
 'best_model_min_trees': 1,
 'model_shrink_rate': 0,
 'min_data_in_leaf': 1,
 'loss_function': 'RMSE',
 'learning_rate': 0.04174000024795532,
 'score_function': 'Cosine',
 'task_type': 'CPU',
 'leaf_estimation_iterations': 1,
 'bootstrap_type': 'MVS',
 'max_leaves': 64}

...
cb = CatBoostRegressor()
...
gsc = GridSearchCV(
    estimator=cb,
    param_grid=param_grid,
    scoring='neg_mean_squared_error', 
    cv=inner_cv, 
    verbose=0,
    return_train_score=True, 
    refit='nmse'
)
...

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-76-a22257b2d93a> in <module>
    113 )
    114 
--> 115 grid_result = runGSCV(2, train, y_train)

<ipython-input-9-594f5556108c> in runGSCV(num_trials, features, y_values)
      7         with MyTimer():
      8             #grid_result = gsc.fit(train, y_train)
----> 9             grid_result = gsc.fit(features, y_values)
     10         non_nested_scores[i] = grid_result.best_score_
     11         if (competition == 'SR'):

~miniconda3envsds_tensorflowlibsite-packagessklearnutilsvalidation.py in inner_f(*args, **kwargs)
     71                           FutureWarning)
     72         kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 73         return f(**kwargs)
     74     return inner_f
     75 

~miniconda3envsds_tensorflowlibsite-packagessklearnmodel_selection_search.py in fit(self, X, y, groups, **fit_params)
    760             # of the params are estimators as well.
    761             self.best_estimator_ = clone(clone(base_estimator).set_params(
--> 762                 **self.best_params_))
    763             refit_start_time = time.time()
    764             if y is not None:

~miniconda3envsds_tensorflowlibsite-packagessklearnutilsvalidation.py in inner_f(*args, **kwargs)
     71                           FutureWarning)
     72         kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 73         return f(**kwargs)
     74     return inner_f
     75 

~miniconda3envsds_tensorflowlibsite-packagessklearnbase.py in clone(estimator, safe)
     86     for name, param in new_object_params.items():
     87         new_object_params[name] = clone(param, safe=False)
---> 88     new_object = klass(**new_object_params)
     89     params_set = new_object.get_params(deep=False)
     90 

TypeError: __init__() got an unexpected keyword argument 'bayesian_matrix_reg'