College application research evidence · understanding and original contribution · Seoul and online

Project courseThe student keeps the work and the record they made.

AI + Games: Agent Studio

Grades 9-12: NavMesh pathfinding in Unity, reward design...

Where this course comes from

The universities and labs named here made the open projects or materials this course draws on. CIT designed the course independently; it is not an official, affiliated, or endorsed course of those institutions.

Where this course's material comes from
  • MITTool used in class
Open protected courseCheck course fit
  • Free consultation and level check
  • Apgujeong classroom or online
  • One-to-one or small group
  • Registered academy no. 11882
A three-layer network diagram running from data through a model to a decision
Quick answer

Is AI + Games: Agent Studio a good fit for high school students in Grades 9-12?

AI + Games: Agent Studio is a good fit for students in grades 9-12 who are interested in NavMesh pathfinding in Unity and reward design for learning agents. CIT offers online or in-person lessons in Apgujeong, Gangnam, Seoul, in one-to-one or small-group formats. Students make a version-pinned Unity repository and build, training logs in TensorBoard and a failure map, and an evaluation report with a release recommendation.

The course runs on MIT Scratch, made by MIT. Students first build a non-learning Unity game in C#, with physics, a score UI, and an enemy that follows NavMesh paths through patrol, chase, attack, and recover states, pinning engine and package versions. They then design ML-Agents observations, actions, and rewards, train with fixed seeds at least three times, and deliberately look for reward hacking, where the agent collects points without reaching the goal. The trained policy is compared with the rule-based enemy on unseen scenes, and the course ends with an audit of AI-suggested code and assets and an evidence-based call to release or hold. The student then designs and tests an extension of their own: a new question, feature, model, interface, or solution. In an application or interview, the student separates the source research from their own decisions, results, failed attempts, revisions, and limits.

Google sign-in is required. Existing account permissions determine access.

My child found the AI classes interesting and stayed with them. It made for a worthwhile school break. Thank you for teaching so attentively.
Parent of a CIT studentTranslated from Korean. One family's experience; the same result is not guaranteed.Read more parent feedback
Age group
Grades 9-12
Academic subject
AI & Data, Arts, Media & DesignBrowse subject
Course type
Course
Format
Online or Apgujeong in person · one-to-one or small group
Teaching language
Korean by default, with complete English materials
Curriculum status
Lesson-readyEvery learning item includes the evidence, worked example, practical work, and tutor guidance required by CIT's lesson-ready standard.

From open research to student-owned work

Students inspect a relevant public source, reproduce the idea, then add an original question, feature, or test. The material this course reads was made at MIT. Names identify the source, not affiliation or endorsement.

Where this course's material comes from
  • MITTool used in class

How can I explain this course to my child?

If questions about NavMesh pathfinding in Unity or reward design for learning agents keep making you ask why, AI + Games: Agent Studio lets you investigate the question with evidence, then build and defend an extension of your own.

Which interests suggest this course?

  • NavMesh pathfinding in Unity
  • reward design for learning agents
  • reproducing agent failures

What does the student finish?A version-pinned Unity repository and build, training logs in TensorBoard and a failure map, and an evaluation report with a release recommendation.

Is this a good fit?

A strong fit for students who want to understand, build, test, or responsibly use AI systems.

Course placement follows current subject and coding readiness.

Students should be ready to document sources, methods, and limits.

Advanced tools are introduced after a clear baseline.

What will my child learn?

  1. Design ML-Agents observation vectors, actions, and episode endings, and check their ranges with heuristic actions before training.
  2. Keep rewards minimal and deliberately find reward hacks where the agent skips the goal and still collects points.
  3. Run the rule-based enemy and the trained policy on the same scenes, seeds, and time budget at least three times and compare means and variance.
  4. Log the sources of AI-suggested code, images, and music, and never merge a change the student cannot explain.
Where this course's material comes from
  • MITTool used in class

How does the course progress?

  1. 1
    Unity Game Baseline

    Build a reference scene from clearly licensed primitive shapes, then wire up Rigidbody physics, a score UI, and a NavMesh enemy.

  2. 2
    Game AI and Telemetry

    Define episode, seed, and reward logs, sanity-check ML-Agents observations and actions, and test the reward for exploits.

  3. 3
    ML-Agents Experiments

    Train with fixed seeds at least three times, then compare the policy with the rule-based enemy on unseen layouts and randomized conditions.

  4. 4
    A Verifiable Agent Game

    Audit AI contributions and asset rights, stress-test a build that has an AI off option, and recommend release or hold.

Students documenting and explaining hands-on work at CIT

What counts as useful evidence?

A version-pinned Unity repository and build, training logs in TensorBoard and a failure map, and an evaluation report with a release recommendation.

What should an admissions reader be able to see?

The course runs on MIT Scratch, made by MIT. The student designs and tests features, models, and screens of their own with it. In an application or interview, the student separates the tool they used from their own decisions, results, failed attempts, revisions, and limits.

Useful evidence may include a documented dataset, baseline comparison, model evaluation, error analysis, and a clear record of the student's own decisions.

These names identify who published the open project the course starts from. The evidence an application reads is what the student understood, completed, and can explain.

Which sources were reviewed?

Catalog reviewed: 2026-09-30

Where this course's material comes from
  • MITTool used in class

Questions parents search before choosing this course

Is AI + Games: Agent Studio a good fit for high school students in Grades 9-12?

AI + Games: Agent Studio is a good fit for students in grades 9-12 who are interested in NavMesh pathfinding in Unity and reward design for learning agents. CIT offers online or in-person lessons in Apgujeong, Gangnam, Seoul, in one-to-one or small-group formats. Students make a version-pinned Unity repository and build, training logs in TensorBoard and a failure map, and an evaluation report with a release recommendation.

Can my child take AI + Games: Agent Studio online or in person, one-to-one or in a small group?

Yes. CIT offers online and in-person lessons at its Apgujeong academy in Gangnam, Seoul, with one-to-one and small-group options. A readiness consultation confirms the available format and starting point for the course.

Does my child need prior subject knowledge or coding experience for AI + Games: Agent Studio?

Course placement follows current subject and coding readiness. Students should be ready to document sources, methods, and limits. Advanced tools are introduced after a clear baseline.

What will my child make or practice in AI + Games: Agent Studio?

The main evidence is a version-pinned Unity repository and build, training logs in TensorBoard and a failure map, and an evaluation report with a release recommendation. Students also document decisions, tests, feedback, and limits in age-appropriate language.

How can AI + Games: Agent Studio show research understanding in a college application?

The course runs on MIT Scratch, made by MIT. The student designs and tests features, models, and screens of their own with it. In an application or interview, the student separates the tool they used from their own decisions, results, failed attempts, revisions, and limits. Useful evidence may include a documented dataset, baseline comparison, model evaluation, error analysis, and a clear record of the student's own decisions.

How are the schedule and tuition for AI + Games: Agent Studio determined?

CIT confirms the student's readiness, goal, location, class size, and current availability before recommending a course plan. The consultation and level check are free; tuition is explained before enrollment.

When should a student start?

There is no fixed intake month. CIT reviews the student's current school term, readiness, and available hours, then names the point in the course where they should begin.

I appreciated that a simple early idea was extended into an 'AI debate tool'. My child has always been interested in debate and social issues, so seeing that interest connect to the project makes me expect a more complete and distinctive result.
Parent of a CIT studentTranslated from Korean. One family's experience; the same result is not guaranteed.Read more parent feedback

Choose the course after a readiness check

CIT can compare this course with nearby options by age, subject, and current preparation.

Request a course mapRun the free profile check