01
Media
MediaHugging Face · 2023 · Hugging Face
Why?
Hands-on units with code if you learn by building.
Loading…
One moment while we fetch this page.
Loading…
One moment while we fetch this page.
Courses, lectures, and readable codebases for getting into deep RL without a paper pile.
For
ML practitioners entering RL who want a course, the classic lecture series, and clean implementations to read.
Covers
Hugging Face Deep RL course, David Silver's DeepMind lectures, Spinning Up, and CleanRL.
The full collection in the community’s reading order.
01
Hugging Face · 2023 · Hugging Face
Why?
Hands-on units with code if you learn by building.
02
David Silver · 2015 · YouTube
Why?
David Silver's DeepMind/UCL lecture playlist. The free grounding in MDPs and classic algorithms.
03
OpenAI · 2018 · OpenAI
Why?
OpenAI's short, opinionated docs on the algorithms you will actually implement.
04
Huang et al. · 2019 · GitHub
Why?
High-quality single-file deep RL implementations. The repo you open when you want every line of PPO or DQN in one place.
05
Yuvraj Singh · 2026 · neatrl.com
Why?
Readable single-file PyTorch RL from scratch - DQN through PPO, SAC - with math-friendly notes beside the code.
YouTube
Docs
Code