Course 4 of 12

Reinforcement Learning Intro

Agents & environments, Q-learning, Policy gradients, and more.

Yiga AI

Advanced en

Advanced · Course · 3 weeks at 5 hrs/week

Duration: 3 weeks
Effort: 5 hrs/week
Lessons: 16
Hands-on exercises: 16
Projects: 1
Language: en

What you’ll learn

Skills you can put to work.

Machine Learning Foundations

Deep Learning with PyTorch

Computer Vision

NLP with Transformers

Syllabus

Every module, step by step.

4 modules · 21 lessons · 14 hours · 1 graded project

840 minutes of guided lesson time.

Module 1 · 5 lessons · 3 hoursAgents & environmentsModule 1 of 4 in Reinforcement Learning Intro.

Overview and set-up
Overview and set-up — Agents & environments in Reinforcement Learning Intro.
Lesson
40 min
Core concepts
Core concepts — Agents & environments in Reinforcement Learning Intro.
Lesson · Locked
40 min
Worked example
Worked example — Agents & environments in Reinforcement Learning Intro.
Lesson · Locked
40 min
Hands-on practice
Hands-on practice — Agents & environments in Reinforcement Learning Intro.
Lesson · Locked
40 min
Module quiz: Agents & environments
Check what you learned in Agents & environments before moving on.
Quiz · Locked
20 min

Module 2 · 5 lessons · 3 hours LockedQ-learningModule 2 of 4 in Reinforcement Learning Intro.

Overview and set-up
Overview and set-up — Q-learning in Reinforcement Learning Intro.
Lesson · Locked
40 min
Core concepts
Core concepts — Q-learning in Reinforcement Learning Intro.
Lesson · Locked
40 min
Worked example
Worked example — Q-learning in Reinforcement Learning Intro.
Lesson · Locked
40 min
Hands-on practice
Hands-on practice — Q-learning in Reinforcement Learning Intro.
Lesson · Locked
40 min
Module quiz: Q-learning
Check what you learned in Q-learning before moving on.
Quiz · Locked
20 min

Module 3 · 5 lessons · 3 hours LockedPolicy gradientsModule 3 of 4 in Reinforcement Learning Intro.

Overview and set-up
Overview and set-up — Policy gradients in Reinforcement Learning Intro.
Lesson · Locked
40 min
Core concepts
Core concepts — Policy gradients in Reinforcement Learning Intro.
Lesson · Locked
40 min
Worked example
Worked example — Policy gradients in Reinforcement Learning Intro.
Lesson · Locked
40 min
Hands-on practice
Hands-on practice — Policy gradients in Reinforcement Learning Intro.
Lesson · Locked
40 min
Module quiz: Policy gradients
Check what you learned in Policy gradients before moving on.
Quiz · Locked
20 min

Module 4 · 6 lessons · 5 hours LockedApplicationsModule 4 of 4 in Reinforcement Learning Intro.

Overview and set-up
Overview and set-up — Applications in Reinforcement Learning Intro.
Lesson · Locked
40 min
Core concepts
Core concepts — Applications in Reinforcement Learning Intro.
Lesson · Locked
40 min
Worked example
Worked example — Applications in Reinforcement Learning Intro.
Lesson · Locked
40 min
Hands-on practice
Hands-on practice — Applications in Reinforcement Learning Intro.
Lesson · Locked
40 min
Module quiz: Applications
Check what you learned in Applications before moving on.
Quiz · Locked
20 min
Graded project: Reinforcement Learning Intro
Apply everything from Reinforcement Learning Intro in one graded, portfolio-ready build.
Graded project · Locked
120 min

Applied learning project

Make the learning visible.

Use Graded project: Reinforcement Learning Intro to apply this course to a practical challenge. You’ll finish with a clear solution and the reasoning behind your choices.

Apply the course’s core skillMake and explain practical decisionsCreate evidence you can share

Your instructor

Joel N.

Career readiness

Connects technical learning to portfolios, interviews and confident career moves.

“The track removed the uncertainty. I knew what to learn next and what to show employers.”
Amina Hassan
Career switcher, Dar es Salaam

Continue with

Your next best step.

Following the order of Machine Learning Engineer.

See the full chain

Next lesson

Overview and set-up

Reinforcement Learning Intro

40 min · Resume

Course 5 in the track

Computer Vision

Image classification, Object detection, Transfer learning, and more.

Intermediate · Course · 4 weeks at 5 hrs/week

Course 6 in the track

Data Pipelines for ML

Feature stores, Airflow, Data validation, and more.

Intermediate · Course · 3 weeks at 5 hrs/week

Course 7 in the track

Edge & Mobile ML

TensorFlow Lite, Quantisation, On-device inference, and more.

Advanced · Course · 3 weeks at 5 hrs/week

Learner reviews

What learners say.

Write a review

Loading reviews…

Previous courseProject: Fraud Detection System End-to-End Next courseComputer Vision

Keep going

Other courses in this track.

View full track

20 lessons · 16.7h · Intermediate

MLOps Fundamentals

Experiment tracking (MLflow), Pipelines, Versioning, and more.

20 lessons · 16.7h · Intermediate

NLP with Transformers

Attention, BERT, Fine-tuning, and more.

24 lessons · 19.3h · Advanced

Project: Fraud Detection System End-to-End

Data, Model, Deployment, and more.

21 lessons · 16.8h · Intermediate

Computer Vision

Image classification, Object detection, Transfer learning, and more.