1.3Standard
An agent acts in an environment and receives rewards.
Improve its policy through trial and error.
Choose two correct statements.
× Incorrect
Reinforcement learning learns a policy from states, actions, and rewards and must balance exploration with exploitation and reward design.
Detailed explanation
IncorrectIt is identical to supervised learning with fixed labels
Interaction and reward are central.
CorrectReinforcement learning learns a policy through states, actions, and rewards
Outcomes are evaluated with a reward signal.
IncorrectNo reward design is needed for safe behavior
A poor reward can encourage unwanted actions.
CorrectBalance exploration of unknown actions with use of known good actions
The agent must trade off learning and exploitation.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 1.3の強化学習、報酬、機械学習方法を確認する。
Official references
What to confirm
強化学習を教師あり学習と区別し、報酬設計の影響を説明できる。
Key points
- State
- Action
- Reward
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Compare the definition with the AIF-C01 objective and the service documentation before applying it.
- Keep the concept separate from a particular answer choice or implementation step.
Foundation review
Reinforcement learning
Learning a policy by taking actions in an environment and receiving feedback.
State
The information describing the environment at a decision point.
Question IDAWS-AIF-235
EnvironmentAWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
Last technical review2026-08-20
Report an error or rights issue