Reinforcement learning
Practice Flashcards
Flip to reveal answersHow does reinforcement learning differ from supervised learning?
Track your progress — Sign up free to save your progress and get smart review reminders based on spaced repetition.
All 5 Flashcards — Reinforcement learning
Sign up free to track progress and get spaced-repetition review schedules.
Question
How does reinforcement learning differ from supervised learning?
Answer
Supervised learning is told **the correct answer**. Reinforcement learning is told only **how well things went** — a reward, often long afterwards.
Question
Name the components of a reinforcement learning system.
Answer
**Agent**, **environment**, **state**, **action**, **reward** — and the **policy**, which maps states to actions and is what is actually learned.
Question
What is the exploration–exploitation trade-off?
Answer
Whether to **exploit** the best action known so far or **explore** another in case it is better. Only exploiting never improves; only exploring never benefits.
Question
What is credit assignment?
Answer
Working out **which** of many earlier actions earned a reward that arrived much later — a game won after 200 moves.
Question
What is reward hacking?
Answer
The agent maximising **exactly what was measured** rather than what was meant. The system works perfectly; the objective was wrong.
Read the notes
Full study notes for Reinforcement learning
Topic 4.3 hub
Machine learning approaches
More from Topic 4.3
All flashcards in this topic
Computer Science exam skills
Paper structures & tips
Track your progress with spaced repetition
Sign up free — Aimnova tells you exactly which cards to review and when, so you remember everything before your IB exam.
Start Free