A robot acts in an environment and receives rewards.
Learn a policy that improves long-term reward.
Choose two correct statements.
Reinforcement learning uses an agent interacting with an environment and learns a policy from rewards.
Detailed explanation
Reinforcement learning learns through interaction and feedback.
Reinforcement learning learns through interaction and feedback.
A policy maps observations or states to actions.
A policy maps observations or states to actions.
Its learning signal is reward, not the same as supervised labels.
Its learning signal is reward, not the same as supervised labels.
The reward design provides the learning objective.
The reward design provides the learning objective.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01ガイドDomain 1.1の強化学習用語を確認する。Expected result
エージェント、環境、行動、報酬、方策の関係を説明できる。Key points
- Agent
- Reward
- Policy
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
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.