Deep Reinforcement Learning Course review
Hugging Face · hugging-face
Train agents that learn by trial and error, from Q-learning up to modern policy methods.
What does it take?
| Difficulty | 4 out of 5 |
|---|---|
| Hours | Not checked yet |
| Format | Reading, Code notebooks, Projects |
| Maths needed | University-level maths |
| Coding needed | Yes, you will write code |
| Hardware needed | Not checked yet |
| Certificate | Free certificate |
| Free to audit | Yes |
| Pace | Self-paced |
| Last updated by the provider | Not checked yet |
Who should take it, and who should skip it?
Take it if you are
- Coders who've done an intro ML course
- Anyone curious about game-playing agents
Skip it if you are
- Beginners
- People who want LLM skills specifically
What will you be able to do after it?
- Explain value-based and policy-based RL
- Train agents in simulated environments
- Share trained agents on the Hugging Face Hub
What's in each module?
| Module | What it covers |
|---|---|
| Foundations | Rewards, policies and value functions. |
| Deep Q-learning | Using neural networks to estimate value. |
| Policy gradient methods | Learning a policy directly. |
What we liked, and what we didn't
What we liked
- Visual, game-based environments
- Clear explanations of hard ideas
- Hands-on every unit
What we didn't
- Maths gets serious
- Some environments are fiddly to set up
What should you take after it?
- Neural Networks: Zero to Hero
Neural Networks: Zero to Hero is 8 free YouTube videos, about 14.5 hours, where Andrej Karpathy builds a GPT from scratch in code. No certificate.
How we rated it: 8.1 out of 10
| Criterion | Score out of 10 |
|---|---|
| Clarity | 8 |
| Hands-on practice | 9 |
| Up to date | 7 |
| Depth | 8 |
| Truly free | 9 |
So should you take it?
The most approachable free route into reinforcement learning, and much more hands-on than university lectures. You'll need to be comfortable with ML basics and some maths.
Where to go next
- Hugging Face Learn: our platform review
What else it offers, and what costs money.
- Machine Learning Specialization
The Machine Learning Specialization has 3 courses and 95 hours of Andrew Ng's lessons. Coursera's FAQ says you cannot take it for free, so check the cost first.
- Hugging Face LLM Course
Hugging Face LLM Course has 12 chapters of 6 to 8 hours each, costs nothing and has no certificate. You learn LLMs with the Transformers library.
- Practical Deep Learning for Coders
Practical Deep Learning for Coders has 9 lessons of about 90 minutes, costs nothing and has no certificate. You deploy your own model by the end of lesson 2.
Last checked .
Not sure this is the one?
Answer two questions and we'll point you to the course that fits where you are today.