Express
AI Line
AI From Zero: Build a Neural Network with NumPy
Rated 4.7 out of 5 from 3 reviewsBeginner 18 lessons 503 students
Fare
€21Reinforcement Learning with Game Agents
Teach agents to play games through trial and error — Q-learning, deep Q-networks and policy gradients.
Rated 4.0 out of 5 from 1 review
- Intermediate
- 20 lessons · 3h 34m of video
- 189 students
- English
- Updated Oct 2026
The route
Curriculum
5 modules · 20 lessons · 3h 34m of video
-
1
29m
Rewards and environments
3 lessons
-
2
41m
Q-learning
4 lessons
-
3
53m
Deep Q-networks
5 lessons
-
4
47m
Policy gradients
4 lessons
-
5
44m
Projects
4 lessons
Destination
What you will be able to do
- Model problems as environments, states and rewards
- Implement Q-learning and deep Q-networks
- Train policy-gradient agents
- Tune exploration and stabilise training
- Record videos of agents playing
Before you board
You will need
- Comfortable Python
- Basic NumPy
About this course
The journey
Reinforcement learning is how an AI learns from rewards instead of examples. You start with a tiny grid world and Q-learning, then move to deep Q-networks for arcade games and policy-gradient methods for continuous control.
Each method is implemented from scratch first and then compared with a standard library, and every agent is shown playing so you can see learning happen.
Frequently asked questions
Still unsure about something? Write to our contact page and a human answers, usually the same working day.
Intermediate. You should be comfortable with the basics listed under requirements.
No. You pay once and keep lifetime access, including every future update to this course.
Yes. The preview video at the top of this page shows real code from the course being written and run.
Checkout is handled on our provider's secure payment page. The moment your payment clears we email your personal access link and access code to the address you used at checkout, and the same link appears in your account library. There is nothing to install and nothing to wait for.
Email within 14 days of your purchase, quote your order number, and we refund the full amount to your original payment method. No form to fill in and no questions about how much of the course you watched.
What students say
Reviews are written by people who bought this course. We publish the critical ones too.
4.0
Rated 4.0 out of 5Course rating · 1 review
Rating distribution
- 5 stars 0%
- 4 stars 100%
- 3 stars 0%
- 2 stars 0%
- 1 star 0%
-
WZAug 2026
Wei Zhang
ML student
Rated 4.0 out of 5Great intuition, needs patience
Watching the agents improve is addictive. Policy gradients are hard and the course does not pretend otherwise; plan extra time for that module.
€85
EUR
One-time payment · lifetime access