Google Cloud Generative AI Leader — Question 3

A company is developing an AI character for a video game. The AI character needs to learn how to navigate a complex environment and make decisions to achieve certain objectives within the game. When the AI takes actions that lead to positive outcomes like finding a reward or overcoming an obstacle, it receives a positive score. When it takes actions that lead to negative outcomes, like hitting a wall or losing progress, it receives a negative score. Through this process of trial and error, the AI gradually improves the character’s ability to play the game effectively. What machine learning should the company use?

Answer options

• A. Unsupervised learning
• B. Reinforcement learning
• C. Supervised learning
• D. Deep learning

Correct answer: B

Explanation

Reinforcement learning is the correct choice because it focuses on training agents to make decisions based on rewards and penalties received from their actions, which aligns perfectly with the described scenario. Unsupervised learning, supervised learning, and deep learning do not involve the feedback mechanism of scores based on actions taken, making them unsuitable for this specific application.