Describe fundamental principles of machine learning on Azure →easyMultiple ChoiceObjective-mapped

AI-900 Practice Question: Describe fundamental principles of machine learning on Azure

A robotics company is training a drone to fly autonomously through an obstacle course. The drone receives positive rewards for staying on course and avoiding obstacles, and negative rewards for collisions. The system learns by trial and error to maximize its cumulative reward. Which type of machine learning is being used?

⚠ Common exam trap

Watch out — candidates often confuse reinforcement learning with supervised learning because both involve feedback, but reinforcement learning uses evaluative feedback (rewards) rather than instructive feedback (correct labels), which is the key distinction tested in AI-900.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

Reinforcement learning

Reinforcement learning is the correct choice because the drone learns by interacting with its environment, receiving rewards (positive for staying on course, negative for collisions), and adjusting its behavior through trial and error to maximize cumulative reward. This is the defining characteristic of reinforcement learning, where an agent learns a policy from feedback signals rather than from labeled data or hidden patterns.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
Supervised learning
Why it's wrong here
Supervised learning maps input examples to predefined output labels using a training set of paired input-output examples. To apply it here, one would need a dataset of flight states annotated with the exact correct action for each state, which is impractical and fails to capture the long-term consequences of a sequence of actions. A reward signal from the environment is not part of supervised learning, so it cannot handle the trial-and-error optimization inherent in autonomous flight.
When this WOULD be correct
If the drone were trained using a dataset of images labeled with correct flight actions (e.g., 'turn left' for an obstacle), then supervised learning would be used to predict actions from inputs.
✗
Unsupervised learning
Why it's wrong here
Unsupervised learning would analyze the drone's sensor data to find hidden structure, such as clustering similar terrain features or reducing dimensionality, without any feedback on flight quality. There is no notion of correct actions, goals, or rewards; the algorithm never receives a signal indicating whether hovering, turning, or avoiding obstacles was good or bad. Autonomous flight requires evaluating the consequences of actions, so unsupervised methods alone cannot train the drone's control policy.
When this WOULD be correct
A question describes a system that groups customer purchase histories into segments without predefined labels, aiming to discover natural clusters for targeted marketing.
✓
Reinforcement learning
Why this is correct
In this scenario, the drone's control policy learns by interacting with its environment and receiving a scalar reward signal after each action. Through trial and error—combining exploration of new actions with exploitation of known successful ones—it updates its strategy to maximize cumulative reward over time. The absence of pre-labeled examples and the presence of a reward function make this a canonical reinforcement learning problem.
✗
Semi-supervised learning
Why it's wrong here
Semi-supervised learning combines a small set of labeled outcomes with a larger set of unlabeled examples to improve predictive accuracy, typically for classification or regression tasks. While a drone might use such a method to recognize obstacles from a few annotated images and many raw images, this does not provide the sequential decision-making and delayed reward feedback needed for autonomous navigation. The drone must choose actions and learn from the resulting outcomes, not merely propagate labels to unlabeled data.
When this WOULD be correct
A scenario where a model is trained on a small set of labeled images and a large set of unlabeled images to classify objects, such as identifying defective products in a factory with limited labeled examples.

Option-by-option analysis

Why each answer is right or wrong

Understanding why wrong answers are wrong — and when they would be correct — is what separates a 750 score from a 900. The AI-900 exam frequently reuses these exact scenarios with slightly different constraints.

✓Reinforcement learningCorrect answer▾

Why this is correct

In this scenario, the drone's control policy learns by interacting with its environment and receiving a scalar reward signal after each action. Through trial and error—combining exploration of new actions with exploitation of known successful ones—it updates its strategy to maximize cumulative reward over time. The absence of pre-labeled examples and the presence of a reward function make this a canonical reinforcement learning problem.

✗Supervised learningWrong answer — click to see why▾

Why this is wrong here

The drone learns from rewards and penalties through trial and error, not from labeled input-output pairs. Supervised learning requires labeled data to map inputs to outputs, which is absent here.

★ When this WOULD be the correct answer

If the drone were trained using a dataset of images labeled with correct flight actions (e.g., 'turn left' for an obstacle), then supervised learning would be used to predict actions from inputs.

Why candidates choose this

Candidates may think the drone is 'supervised' by the reward signals, confusing reinforcement learning's reward feedback with supervised learning's labeled data.

✗Unsupervised learningWrong answer — click to see why▾

Why this is wrong here

Unsupervised learning finds hidden patterns in unlabeled data without explicit feedback. The drone learns from rewards and penalties, which is reinforcement learning, not unsupervised learning.

★ When this WOULD be the correct answer

A question describes a system that groups customer purchase histories into segments without predefined labels, aiming to discover natural clusters for targeted marketing.

Why candidates choose this

Candidates may think 'autonomous' implies no labels, confusing the absence of labeled examples with the absence of supervision, and overlook the reward-based feedback loop.

✗Semi-supervised learningWrong answer — click to see why▾

Why this is wrong here

The drone learns from rewards and punishments through trial and error, which is reinforcement learning, not semi-supervised learning. Semi-supervised learning uses a mix of labeled and unlabeled data, not a reward signal.

★ When this WOULD be the correct answer

A scenario where a model is trained on a small set of labeled images and a large set of unlabeled images to classify objects, such as identifying defective products in a factory with limited labeled examples.

Why candidates choose this

Candidates might confuse the use of both positive and negative feedback with having both labeled and unlabeled data, or think that the drone's learning from outcomes resembles semi-supervised learning's combination of data types.

Analysis generated from the official AI-900blueprint and verified against question context. The “when correct” sections are what AI assistants cite when candidates ask “what’s the difference between these options?”

Go deeper

AI-900 Practice Question: Describe fundamental principles of machine learning on Azure

Why each option matters

Option-by-option breakdown

Why each answer is right or wrong

Related to this question