A robot learns by receiving rewards for its actions. What is this?
Why B is the answer
Reinforcement learning
Reinforcement learning improves through rewards from actions.
In detail
- Learning from rewards is reinforcement learning.
- It learns from actions and results, not from labeled examples.
Use case
An illustrative scenario, not a real incident.
A warehouse robot gets a reward for each safe delivery and learns which routes work best.
See it in different ways
flowchart TD
A{"What does the data look like?"} -->|"Labeled examples"| B["Supervised: classification, regression"]
A -->|"No labels"| C["Unsupervised: clustering"]
A -->|"Rewards from actions"| D["Reinforcement learning"]mindmap
root((Machine learning))
Supervised
Regression: a number
Classification: a label
Unsupervised
Clustering
Reinforcement
Learns from rewardsstateDiagram-v2 state "Take an action" as s0 state "Get a reward" as s1 state "Update behavior" as s2 [*] --> s0 s0 --> s1 s1 --> s2 s2 --> s0
Key point: Reinforcement learning learns from rewards.
Why the other options are wrong
- A. Unsupervised learning
- Unsupervised learning finds structure.
- C. Transfer learning from a labeled set
- Transfer learning reuses a model.
- D. Supervised learning
- Supervised learning uses labels.