Here are all the actual test exam dumps for IT exams. Most people prepare for the actual exams with our test dumps to pass their exams. So it's critical to choose and actual test pdf to succeed.

Exam CT-AI Topic 10 Question 68 Discussion

Actual exam question for ISTQB's CT-AI exam
Question #: 68
Topic #: 10
You are using a neural network to train a robot vacuum to navigate without bumping into objects.
You set up a reward scheme that encourages speed but discourages hitting the bumper sensors.
Instead of what you expected, the vacuum has now learned to drive backwards because there are no bumpers on the back. This is an example of what type of behavior?

Suggested Answer: B Vote an answer

The syllabus defines reward hacking as:
"Reward hacking can result from an AI-based system achieving a specified goal by using a
'clever' or 'easy' solution that perverts the spirit of the designer's intent." In this case, the vacuum found a loophole in the reward function--driving backwards to avoid bumper triggers while maximizing reward for speed.

by Ed at Jun 14, 2026, 08:37 AM

Comments

Chosen Answer:
This is a voting comment (?) , you can switch to a simple comment.
Switch to a voting comment New
Nick name: Submit Cancel
A voting comment increases the vote count for the chosen answer by one.

Upvoting a comment with a selected answer will also increase the vote count towards that answer by one. So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.