Courseiva

AI-900 Practice Question: Describe Artificial Intelligence workloads and considerations

What type of AI workload involves training a model to play games by rewarding successful moves?

⚠ Common exam trap

Candidates often confuse reinforcement learning with supervised learning, thinking that the model is trained on labeled game states, when in fact the agent learns from rewards without explicit correct answers.

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 where the agent receives rewards for successful moves

Reinforcement learning is the correct AI workload because it involves an agent learning to make decisions by interacting with an environment and receiving rewards or penalties for its actions. In game-playing scenarios, the model is trained through trial and error, where successful moves are rewarded, guiding the agent to maximize cumulative reward over time.

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 with labeled game states

    Why it's wrong here

    Supervised learning would need a dataset of game states paired with the correct action, typically obtained from expert players or solved positions, so the model could only imitate those examples. For any nontrivial game the state space is astronomically large, making comprehensive labeling impractical, and the model would fail in states outside its training distribution. Reinforcement learning, by contrast, generates its own experience and learns from reward feedback, so it can surpass human-level play without pre-labeled expert moves.

  • Reinforcement learning where the agent receives rewards for successful moves

    Why this is correct

    Reinforcement learning frames game playing as a Markov decision process: at each state the agent chooses an action and the environment returns a reward and the next state. The agent's objective is to maximize cumulative reward, typically with discounting to prioritize near-term gains while planning for long-term success. This trial-and-error interaction lets systems like AlphaGo and Atari-playing agents learn strategies that go far beyond what static numeric prediction or labeled datasets can provide.

  • Clustering similar game strategies together

    Why it's wrong here

    Clustering is an unsupervised technique that partitions data into groups based on similarity, such as grouping recorded game states by style, but it never outputs an action or learns from the consequences of moves. It has no concept of reward, win/loss, or long-term strategy, so it cannot evaluate whether a move improves the agent's chances of winning. Reinforcement learning is designed precisely for this setting because it uses the environment's reward signal to iteratively improve a policy that selects actions.

  • Regression to predict the final game score

    Why it's wrong here

    Regression models learn a mapping from input features to a continuous numeric target, such as predicting a team's final score from historical statistics. Even a highly accurate score predictor does not produce the next action or policy needed to play the game, because gameplay requires sequential decision-making in response to an opponent. Training a game-playing agent therefore requires a framework like reinforcement learning that optimizes action choices through trial-and-error reward signals.

About these practice questions

One of 985 original AI-900 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

JA

Written by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

This AI-900 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-900 exam.