feat(curriculum): add python multiple choice questions (#38890)

2020-05-28 22:40:36 +09:00
parent 18d2dca05b
commit 3567813c51
98 changed files with 1118 additions and 398 deletions
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/conclusion.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/conclusion.english.md
@ -15,12 +15,13 @@ videoId: LMNub5frQi4

 ```yml
 question:
-  text: Question
+  text: |
+    Most people that are experts in AI or machine learning usually...:
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - have one specialization.
+    - have many specializations.
+    - have a deep understanding of many different frameworks.
+  solution: 1
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/convolutional-neural-networks-evaluating-the-model.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/convolutional-neural-networks-evaluating-the-model.english.md
@ -15,11 +15,11 @@ videoId: eCATNvwraXg

 ```yml
 question:
-  text: Question
+  text: What is **not** a good way to increase the accuracy of a convolutional neural network?
  answers:
-    - one
-    - two
-    - three
+    - Augmenting the data you already have.
+    - Using a pre-trained model.
+    - Using your test data to retrain the model.
  solution: 3
 ```

--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/convolutional-neural-networks-picking-a-pretrained-model.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/convolutional-neural-networks-picking-a-pretrained-model.english.md
@ -15,12 +15,36 @@ videoId: h1XUt1AgIOI

 ```yml
 question:
-  text: Question
+  text: |
+    Fill in the blanks below to use Google's pre-trained MobileNet V2 model as a base for a convolutional neural network:
+
+    ```py
+    base_model = tf.__A__.applications.__B__(input_shape=(160, 160, 3),
+                                                   include_top=__C__,
+                                                   weights='imagenet'
+                                                   )
+    ```
+
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - |
+      A: `keras`
+
+      B: `MobileNetV2`
+
+      C: `False`
+    - |
+      A: `Keras`
+
+      B: `MobileNetV2`
+
+      C: `True`
+    - |
+      A: `keras`
+
+      B: `mobile_net_v2`
+
+      C: `False`
+  solution: 1
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/convolutional-neural-networks-the-convolutional-layer.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/convolutional-neural-networks-the-convolutional-layer.english.md
@ -15,12 +15,12 @@ videoId: LrdmcQpTyLw

 ```yml
 question:
-  text: Question
+  text: What are the three main properties of each convolutional layer?
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - Input size, the number of filters, and the sample size of the filters.
+    - Input size, input dimensions, and the color values of the input.
+    - Input size, input padding, and stride.
+  solution: 1
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/convolutional-neural-networks.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/convolutional-neural-networks.english.md
@ -15,11 +15,12 @@ videoId: _1kTP7uoU9E

 ```yml
 question:
-  text: Question
+  text: |
+    Dense neural networks analyze input on a global scale and recognize patterns in specific areas. Convolutional neural networks...:
  answers:
-    - one
-    - two
-    - three
+    - also analyze input globally and extract features from specific areas.
+    - do not work well for image classification or object detection.
+    - scan through the entire input a little at a time and learn local patterns.
  solution: 3
 ```

--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms-building-the-model.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms-building-the-model.english.md
@ -15,12 +15,15 @@ videoId: 5wHw8BTd2ZQ

 ```yml
 question:
-  text: Question
+  text: What kind of estimator/model does TensorFlow recommend using for classification?
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - |
+      `LinearClassifier`
+    - |
+      `DNNClassifier`
+    - |
+      `BoostedTreesClassifier`
+  solution: 2
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms-classification.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms-classification.english.md
@ -15,12 +15,12 @@ videoId: qFF7ZQNvK9E

 ```yml
 question:
-  text: Question
+  text: What is classification?
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - The process of separating data points into different classes.
+    - Predicting a numeric value or forecast based on independent and dependent variables.
+    - None of the above.
+  solution: 1
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms-clustering.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms-clustering.english.md
@ -15,12 +15,14 @@ videoId: 8sqIaHc9Cz4

 ```yml
 question:
-  text: Question
+  text: Which of the following steps is **not** part of the K-Means algorithm?
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - Randomly pick K points to place K centeroids.
+    - Assign each K point to the closest K centeroid.
+    - Move each K centeroid into the middle of all of their data points.
+    - Shuffle the K points so they're redistributed randomly.
+    - Reassign each K point to the closest K centeroid.
+  solution: 4
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms-hidden-markov-models.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms-hidden-markov-models.english.md
@ -15,12 +15,12 @@ videoId: IZg24y4wEPY

 ```yml
 question:
-  text: Question
+  text: What makes a Hidden Markov model different than linear regression or classification?
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - It uses probability distributions to predict future events or states.
+    - It analyzes the relationship between independent and dependent variables to make predictions.
+    - It separates data points into separate categories. 
+  solution: 1
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms-the-training-process.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms-the-training-process.english.md
@ -15,12 +15,12 @@ videoId: _cEwvqVoBhI

 ```yml
 question:
-  text: Question
+  text: What are epochs?
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - The number of times the model will see the same data.
+    - A type of graph.
+    - The number of elements you feed to the model at once.
+  solution: 1
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms-training-and-testing-data.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms-training-and-testing-data.english.md
@ -15,12 +15,12 @@ videoId: wz9J1slsi7I

 ```yml
 question:
-  text: Question
+  text: What is categorical data?
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - Another term for one-hot encoding.
+    - Any data that is not numeric.
+    - Any data that is represented numerically.
+  solution: 2
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms-using-probabilities-to-make-predictions.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms-using-probabilities-to-make-predictions.english.md
@ -15,11 +15,14 @@ videoId: fYAYvLUawnc

 ```yml
 question:
-  text: Question
+  text: What TensorFlow module should you import to implement `.HiddenMarkovModel()`?
  answers:
-    - one
-    - two
-    - three
+    - |
+      `tensorflow.keras`
+    - |
+      `tensorflow_gpu`
+    - |
+      `tensorflow_probability`
  solution: 3
 ```

--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms-working-with-data.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms-working-with-data.english.md
@ -15,11 +15,12 @@ videoId: u85IOSsJsPI

 ```yml
 question:
-  text: Question
+  text: |
+    What does the pandas `.head()` function do?
  answers:
-    - one
-    - two
-    - three
+    - Returns the number of entries in a data frame.
+    - Returns the number of columns in a data frame.
+    - By default, shows the first five rows or entries in a data frame.
  solution: 3
 ```

--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/core-learning-algorithms.english.md
@ -15,12 +15,16 @@ videoId: u5lZURgcWnU

 ```yml
 question:
-  text: Question
+  text: |
+    Which type of analysis would be best suited for the following problem?: 
+    
+    You have the average temperature in the month of March for the last 100 years. Using this data, you want to predict the average temperature in the month of March 5 years from now.
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - Multiple regression
+    - Correlation
+    - Decision tree
+    - Linear regression
+  solution: 4
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/creating-a-convolutional-neural-network.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/creating-a-convolutional-neural-network.english.md
@ -15,11 +15,38 @@ videoId: kfv0K8MtkIc

 ```yml
 question:
-  text: Question
+  text: |
+    Fill in the blanks below to complete the architechture for a convolutional neural network:
+
+    ```py
+    model = models.__A__()
+    model.add(layers.__B__(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))
+    model.add(layers.__C__(2, 2))
+    model.add(layers.__B__(64, (3, 3), activation='relu'))
+    model.add(layers.__C__(2, 2))
+    model.add(layers.__B__(32, (3, 3), activation='relu'))
+    model.add(layers.__C__(2, 2))
+    ```
+
  answers:
-    - one
-    - two
-    - three
+    - |
+      A: `Sequential`
+
+      B: `add`
+
+      C: `Wrapper`
+    - |
+      A: `keras`
+
+      B: `Cropping2D`
+
+      C: `AlphaDropout`
+    - |
+      A: `Sequential`
+
+      B: `Conv2D`
+
+      C: `MaxPooling2D`
  solution: 3
 ```

--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/introduction-machine-learning-fundamentals.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/introduction-machine-learning-fundamentals.english.md
@ -15,12 +15,13 @@ videoId: KwL1qTR5MT8

 ```yml
 question:
-  text: Question
+  text: |
+    Which statement below is **false**?
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - Neural networks are modeled after the way the human brain works.
+    - Computer programs that play tic-tac-toe or chess against human players are examples of simple artificial intelligence.
+    - Machine learning is a subset of artificial intelligence.
+  solution: 1
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/introduction-to-tensorflow.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/introduction-to-tensorflow.english.md
@ -15,12 +15,14 @@ videoId: r9hRyGGjOgQ

 ```yml
 question:
-  text: Question
+  text: Which of the following is **not** a type of tensor?
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - Variable
+    - Flowing
+    - Placeholder
+    - SparseTensor
+    - Constant
+  solution: 2
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-building-the-model.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-building-the-model.english.md
@ -15,11 +15,48 @@ videoId: 32WBFS7lfsw

 ```yml
 question:
-  text: Question
+  text: |
+    Fill in the blanks below to complete the `build_model` function:
+
+    ```py
+    def build_mode(vocab_size, embedding_dim, rnn_units, batch_size):
+        model = tf.keras.Sequential([
+            tf.keras.layers.Embedding(vocab_size,
+                                      embedding_dim, 
+                                      batch_input_shape=[batch_size, None]),
+            tf.keras.layers.__A__(rnn_units,
+                                  return_sequences=__B__,
+                                  recurrent_initializer='glorot_uniform),
+            tf.keras.layers.Dense(__C__)
+        ])
+        __D__
+    ```
+
  answers:
-    - one
-    - two
-    - three
+    - |
+      A: `ELU`
+
+      B: `True`
+
+      C: `vocab_size`
+
+      D: `return model`
+    - |
+      A: `LSTM`
+
+      B: `False`
+
+      C: `batch_size`
+
+      D: `return model`
+    - |
+      A: `LSTM`
+
+      B: `True`
+
+      C: `vocab_size`
+
+      D: `return model`
  solution: 3
 ```

--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-create-a-play-generator.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-create-a-play-generator.english.md
@ -15,12 +15,28 @@ videoId: j5xsxjq_Xk8

 ```yml
 question:
-  text: Question
+  text: |
+
+    Fill in the blanks below to create the training examples for the RNN:
+
+    ```py
+    char_dataset = tf.data.__A__.__B__(text_as_int)
+    ```
+
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - |
+      A: `DataSet`
+
+      B: `from_tensor_slices`
+    - |
+      A: `data`
+
+      B: `from_tensors`
+    - |
+      A: `DataSet`
+
+      B: `from_generator`
+  solution: 1
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-making-predictions.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-making-predictions.english.md
@ -15,12 +15,13 @@ videoId: WO1hINnBj20

 ```yml
 question:
-  text: Question
+  text: |
+    Before you make a prediction with your own review, you should...:
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - decode the training dataset and compare the results to the test data.
+    - use the encodings from the training dataset to encode your review.
+    - assign random values between 0 and the maximum number of vocabulary in your dataset to each word in your review.
+  solution: 2
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-part-2.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-part-2.english.md
@ -15,11 +15,12 @@ videoId: mUU9YXOFbZg

 ```yml
 question:
-  text: Question
+  text: |
+    Word embeddings are...:
  answers:
-    - one
-    - two
-    - three
+    - an unordered group of encoded words that describes the frequency of words in a given document.
+    - a group of encoded words that preserves the original order of the words in a given document.
+    - a vectorized representation of words in a given document that places words with similar meanings near each other.
  solution: 3
 ```

--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-recurring-neural-networks.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-recurring-neural-networks.english.md
@ -15,12 +15,17 @@ videoId: bX5681NPOcA

 ```yml
 question:
-  text: Question
+  text: What is true about Recurrent Neural Networks?
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - |
+      1: They are a type of feed-forward neural network.
+    - |
+      2: They maintain an internal memory/state of the input that was already processed.
+    - |
+      3: RNN's contain a loop and process one piece of input at a time.
+    - |
+      4: Both 2 and 3.
+  solution: 4
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-sentimental-analysis.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-sentimental-analysis.english.md
@ -15,11 +15,36 @@ videoId: lYeLtu8Nq7c

 ```yml
 question:
-  text: Question
+  text: |
+    Fill in the blanks below to create the model for the RNN:
+
+    ```py
+    model = __A__.keras.Sequential([
+        __A__.keras.layers.__B__(88584, 32),
+        __A__.keras.layers.__C__(32),
+        __A__.keras.layers.DENSE(1, activation='sigmoid')
+    ])
+    ```
+
  answers:
-    - one
-    - two
-    - three
+    - |
+      A: `tensor_flow`
+
+      B: `embedding`
+
+      C: `LSTM`
+    - |
+      A: `tf`
+
+      B: `Embedding`
+
+      C: `AlphaDropout`
+    - |
+      A: `tf`
+
+      B: `Embedding`
+
+      C: `LSTM`
  solution: 3
 ```

--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-training-the-model.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-training-the-model.english.md
@ -15,12 +15,41 @@ videoId: hEUiK7j9UI8

 ```yml
 question:
-  text: Question
+  text: |
+    Fill in the blanks below to save your model's checkpoints in the `./checkpoints` directory and call the latest checkpoint for training:
+
+    ```py
+    checkpoint_dir = __A__
+    checkpoint_prefix = os.path.join(checkpoint_dir, 'ckpt_{epoch}')
+
+    checkpoint_callback = tf.keras.callbacks.__B__(
+        filepath=checkpoint_prefix,
+        save_weights_only=True
+    )
+
+    history = model.fit(data, epochs=2, callbacks=[__C__])
+    ```
+
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - |
+      A: `'./training_checkpoints'`
+
+      B: `ModelCheckpoint`
+
+      C: `checkpoint_prefix`
+    - |
+      A: `'./checkpoints'`
+
+      B: `ModelCheckpoint`
+
+      C: `checkpoint_callback`
+    - |
+      A: `'./checkpoints'`
+
+      B: `BaseLogger`
+
+      C: `checkpoint_callback`
+  solution: 2
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns.english.md
@ -15,12 +15,13 @@ videoId: ZyCaF5S-lKg

 ```yml
 question:
-  text: Question
+  text: |
+    Natural Language Processing is a branch of artifitial intelligence that...:
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - deals with how computers understand and process natural/human languages.
+    - translates image data into natural/human languages.
+    - is focused on translating computer languages into natural/human languages.
+  solution: 1
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/neural-networks-activation-functions.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/neural-networks-activation-functions.english.md
@ -15,12 +15,12 @@ videoId: S45tqW6BqRs

 ```yml
 question:
-  text: Question
+  text: Which activation function switches values between -1 and 1?
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - Relu (Rectified Linear Unit)
+    - Tanh (Hyperbolic Tangent)
+    - Sigmoid
+  solution: 2
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/neural-networks-creating-a-model.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/neural-networks-creating-a-model.english.md
@ -15,12 +15,37 @@ videoId: K8bz1bmOCTw

 ```yml
 question:
-  text: Question
+  text: |
+    Fill in the blanks below to build a sequential model of dense layers:
+
+    ```py
+    model = __A__.__B__([
+        __A__.layers.Flatten(input_shape=(28, 28)),
+        __A__.layers.__C__(128, activation='relu'),
+        __A__.layers.__C__(10, activation='softmax')
+    ])
+    ```
+
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - |
+      A: `keras`
+      
+      B: `Sequential`
+      
+      C: `Dense`
+    - |
+      A: `tf`
+      
+      B: `Sequential`
+      
+      C: `Categorical`
+    - |
+      A: `keras`
+      
+      B: `sequential`
+      
+      C: `dense`
+  solution: 1
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/neural-networks-optimizers.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/neural-networks-optimizers.english.md
@ -15,12 +15,12 @@ videoId: hdOtRPQe1o4

 ```yml
 question:
-  text: Question
+  text: What is an optimizer function?
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - A function that increases the accuracy of a model's predictions.
+    - A function that implements the gradient descent and backpropogation algorithms for you.
+    - A function that reduces the time a model needs to train.
+  solution: 2
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/neural-networks-with-tensorflow.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/neural-networks-with-tensorflow.english.md
@ -15,11 +15,12 @@ videoId: uisdfrNrZW4

 ```yml
 question:
-  text: Question
+  text: |
+    A densely connected neural network is one in which...:
  answers:
-    - one
-    - two
-    - three
+    - all the neurons in the current layer are connected to one neuron in the previous layer.
+    - all the neurons in each layer are connected randomly.
+    - all the neurons in the current layer are connected to every neuron in the previous layer.
  solution: 3
 ```

--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/reinforcement-learning-with-q-learning-example.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/reinforcement-learning-with-q-learning-example.english.md
@ -15,12 +15,33 @@ videoId: RBBSNta234s

 ```yml
 question:
-  text: Question
+  text: |
+    Fill in the blanks to complete the following Q-Learning equation:
+
+    ```py
+    Q[__A__, __B__] = Q[__A__, __B__] + LEARNING_RATE * (reward + GAMMA * np.max(Q[__C__, :]) - Q[__A__, __B__])
+    ```
+
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - |
+      A: `state`
+
+      B: `action`
+
+      C: `next_state`
+    - |
+      A: `state`
+
+      B: `action`
+
+      C: `prev_state`
+    - |
+      A: `state`
+
+      B: `reaction`
+
+      C: `next_state`
+  solution: 1
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/reinforcement-learning-with-q-learning-part-2.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/reinforcement-learning-with-q-learning-part-2.english.md
@ -15,12 +15,11 @@ videoId: DX7hJuaUZ7o

 ```yml
 question:
-  text: Question
+  text: What can happen if the agent does not have a good balance of taking random actions and using learned actions?
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - The agent will always try to minimize its reward for the current state/action, leading to local minima.
+    - The agent will always try to maximize its reward for the current state/action, leading to local maxima.
+  solution: 2
 ```

 </section>
--- a/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/reinforcement-learning-with-q-learning.english.md
+++ b/curriculum/challenges/english/11-machine-learning-with-python/tensorflow/reinforcement-learning-with-q-learning.english.md
@ -15,12 +15,12 @@ videoId: Cf7DSU0gVb4

 ```yml
 question:
-  text: Question
+  text: The key components of reinforcement learning are...
  answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - environment, representative, state, reaction, and reward.
+    - environment, agent, state, action, and reward.
+    - habitat, agent, state, action, and punishment.
+  solution: 2
 ```

 </section>