Câu 14: 612-51: Certified Responsible AI Governance and Ethics Professional

AutoWarehousing is deploying autonomous robots to navigate a complex, changing warehouse floor. The robots are not given a map; instead, they must learn to navigate by trial and error, receiving a “reward” signal when they successfully reach a destination and a “penalty” when they hit an obstacle. Which machine learning approach describes this learning process?

1. A. Unsupervised Learning
2. B. Reinforcement Learning — đáp án hiện tại
3. C. Semi-Supervised Learning
4. D. Supervised Learning