diff --git a/autosklearn/automl.py b/autosklearn/automl.py
index c392065ee7..4f922049de 100644
--- a/autosklearn/automl.py
+++ b/autosklearn/automl.py
@@ -172,8 +172,8 @@ def __init__(self,
                  memory_limit=3072,
                  metadata_directory=None,
                  debug_mode=False,
-                 include=None,
-                 exclude=None,
+                 include: Optional[Dict[str, List[str]]] = None,
+                 exclude: Optional[Dict[str, List[str]]] = None,
                  resampling_strategy='holdout-iterative-fit',
                  resampling_strategy_arguments=None,
                  n_jobs=None,
@@ -1844,10 +1844,14 @@ def show_models(self):
 
             return sio.getvalue()
 
-    def _create_search_space(self, tmp_dir, backend, datamanager,
-                             include=None,
-                             exclude=None,
-                             ):
+    def _create_search_space(
+        self,
+        tmp_dir,
+        backend,
+        datamanager,
+        include: Optional[Dict[str, List[str]]] = None,
+        exclude: Optional[Dict[str, List[str]]] = None,
+    ):
         task_name = 'CreateConfigSpace'
 
         self._stopwatch.start_task(task_name)
diff --git a/autosklearn/estimators.py b/autosklearn/estimators.py
index f38b58cc44..256c47934c 100644
--- a/autosklearn/estimators.py
+++ b/autosklearn/estimators.py
@@ -34,8 +34,8 @@ def __init__(
         max_models_on_disc=50,
         seed=1,
         memory_limit=3072,
-        include=None,
-        exclude=None,
+        include: Optional[Dict[str, List[str]]] = None,
+        exclude: Optional[Dict[str, List[str]]] = None,
         resampling_strategy='holdout',
         resampling_strategy_arguments=None,
         tmp_folder=None,
@@ -97,24 +97,63 @@ def __init__(
             Memory limit in MB for the machine learning algorithm.
             `auto-sklearn` will stop fitting the machine learning algorithm if
             it tries to allocate more than ``memory_limit`` MB.
-            
-            **Important notes:** 
-            
+
+            **Important notes:**
+
             * If ``None`` is provided, no memory limit is set.
-            * In case of multi-processing, ``memory_limit`` will be *per job*, so the total usage is 
+            * In case of multi-processing, ``memory_limit`` will be *per job*, so the total usage is
               ``n_jobs x memory_limit``.
             * The memory limit also applies to the ensemble creation process.
 
-        include : dict, optional (None)
-            If None, all possible algorithms are used. Otherwise specifies
-            set of algorithms for each added component is used. Include and 
-            exclude are incompatible if used together on the same component
+        include : Optional[Dict[str, List[str]]] = None
+            If None, all possible algorithms are used.
+
+            Otherwise, specifies a step and the components that are included in search.
+            See ``/pipeline/components/<step>/*`` for available components.
+
+            Incompatible with parameter ``exclude``.
+
+            **Possible Steps**:
+
+            * ``"data_preprocessor"``
+            * ``"balancing"``
+            * ``"feature_preprocessor"``
+            * ``"classifier"`` - Only for when when using ``AutoSklearnClasssifier``
+            * ``"regressor"`` - Only for when when using ``AutoSklearnRegressor``
+
+            **Example**:
+
+            .. code-block:: python
+
+                include = {
+                    'classifier': ["random_forest"],
+                    'feature_preprocessor': ["no_preprocessing"]
+                }
+
+        exclude : Optional[Dict[str, List[str]]] = None
+            If None, all possible algorithms are used.
+
+            Otherwise, specifies a step and the components that are excluded from search.
+            See ``/pipeline/components/<step>/*`` for available components.
+
+            Incompatible with parameter ``include``.
+
+            **Possible Steps**:
+
+            * ``"data_preprocessor"``
+            * ``"balancing"``
+            * ``"feature_preprocessor"``
+            * ``"classifier"`` - Only for when when using ``AutoSklearnClasssifier``
+            * ``"regressor"`` - Only for when when using ``AutoSklearnRegressor``
+
+            **Example**:
+
+            .. code-block:: python
 
-        exclude : dict, optional (None)
-            If None, all possible algorithms are used. Otherwise specifies
-            set of algorithms for each added component is not used.
-            Incompatible with include. Include and exclude are incompatible
-            if used together on the same component
+                exclude = {
+                    'classifier': ["random_forest"],
+                    'feature_preprocessor': ["no_preprocessing"]
+                }
 
         resampling_strategy : string or object, optional ('holdout')
             how to to handle overfitting, might need 'resampling_strategy_arguments'
diff --git a/autosklearn/smbo.py b/autosklearn/smbo.py
index 696e415a4b..3cb823f2ff 100644
--- a/autosklearn/smbo.py
+++ b/autosklearn/smbo.py
@@ -1,3 +1,4 @@
+from typing import Dict, List, Optional
 import copy
 import json
 import logging
@@ -231,8 +232,8 @@ def __init__(self, config_space, dataset_name,
                  metadata_directory=None,
                  resampling_strategy='holdout',
                  resampling_strategy_args=None,
-                 include=None,
-                 exclude=None,
+                 include: Optional[Dict[str, List[str]]] = None,
+                 exclude: Optional[Dict[str, List[str]]] = None,
                  disable_file_output=False,
                  smac_scenario_args=None,
                  get_smac_object_callback=None,