Software Engineering › Key terms › Y12 Software Automation › Reinforcement learning
Reinforcement learning
Term Key terms bank Y12 Software Automation
Definition
The model learns by trial and error, receiving rewards or penalties for its actions in an environment, to maximise reward.
Example: A robot learns to walk by being rewarded.
Found in: syllabus, sample exam and familiarisation guidelines, school notes.
Learn from rewards and penalties.
Where it is used in the test
Syllabus area: Y12 Software Automation.
Question types it can appear in
- Multiple choice: Pick the option that matches the definition or example.
- Matching or table: Match it to its description, example or category.
- Short answer: Define, outline or explain it and tie it to the scenario.
- Fill in the blanks: Choose this term to complete a statement or table.
Where it has appeared in the paper
Software Automation (Part A). Part letters follow each paper’s own layout.
Related past questions
- 2025 HSC Q3 (1 mark): Machine learning training Software Automation (Part A) · 1 mark
These are the questions the flashcard set links to this term. Open each one and compare your answer with its marking criteria.
Study links
- Flashcard: Reinforcement learning in Software Automation (Year 12) · study that set
- Memorise: Models of training ML
- Key terms bank entry: Reinforcement learning
- Notes: Explore models of training ML, including supervised learning, unsupervised learning,… (Software Automation (Year 12))
- Notes: Investigate common applications of key ML algorithms, including data analysis and… (Software Automation (Year 12))
How to use it in an answer
A model sentence
“The model learns by trial and error, receiving rewards or penalties for its actions in an environment, to maximise reward.” Then apply it: A robot learns to walk by being rewarded.
In a short answer, give the definition in your own words first, then tie it to the situation in the question. Do not copy the example above unless it fits the scenario.
Command words used with it
- Identify: Recognise and name. (2025 HSC Q3 (1 mark): Machine learning training)
Technique for the question types
- Multiple choice: Read all four options, rule out wrong ones, pick one; no penalty for guessing so never leave blank.
- Matching or table: Tick or match each statement to the right column (for example ORM v SQL, SAST v DAST).
- Short answer: One clear point per mark, use the stimulus and course terms, and answer the command word.
- Fill in the blanks: Choose the right word from a list; use exact syllabus terms.
Common mistakes
- Use the term exactly as the syllabus words it, then link it to the scenario in the question; the 2025 feedback repeatedly rewards using the stimulus.
- Answer the command word: outline gives main points only, explain gives a reason or cause, discuss gives both sides.
Related terms
Same group in the syllabus: Supervised learning · Unsupervised learning · Semi-supervised learning · Training data and test data