Types of ML (supervised, unsupervised, reinforcement) in ML Python - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Identify the type of learning from a description

You have a dataset with labeled images of cats and dogs. You want the model to learn to tell cats from dogs using these labels. What type of machine learning is this?

A Unsupervised learning

B Supervised learning

C Reinforcement learning

D Self-supervised learning

❓ Predict Output

intermediate

Output of clustering algorithm example

What is the output of this Python code using KMeans clustering on simple 2D points?

ML Python

from sklearn.cluster import KMeans
import numpy as np
points = np.array([[1,2],[1,4],[1,0],[10,2],[10,4],[10,0]])
kmeans = KMeans(n_clusters=2, random_state=0).fit(points)
labels = kmeans.labels_
print(labels.tolist())

A [0, 0, 0, 1, 1, 1]

B [1, 1, 1, 0, 0, 0]

C [0, 1, 0, 1, 0, 1]

D [1, 0, 1, 0, 1, 0]

❓ Model Choice

advanced

Choosing the right ML type for a game AI

You want to build an AI that learns to play a video game by trying moves and getting points as feedback. Which type of machine learning should you use?

A Supervised learning

B Unsupervised learning

C Reinforcement learning

D Semi-supervised learning

❓ Metrics

advanced

Evaluating clustering quality

Which metric is commonly used to evaluate the quality of an unsupervised clustering model?

A Cross-entropy loss

B Accuracy

C Mean squared error

D Silhouette score

🔧 Debug

expert

Why does this reinforcement learning code not update the policy?

Consider this simplified reinforcement learning code snippet. Why does the policy not improve after training?

ML Python

import numpy as np
policy = np.array([0.5, 0.5])
rewards = [1, -1, 1, -1]
actions = [0, 1, 0, 1]
for r, a in zip(rewards, actions):
    policy[a] += 0.1 * r
policy = policy / policy.sum()
print(policy)

A Policy probabilities can become negative causing invalid distribution

B Normalization divides by sum but sum can be zero causing error

C Learning rate 0.1 is too small to update policy noticeably

D Rewards are not used to update the policy correctly