#5454th of 65 in Learning and cookbooks
practical_rl
Open reinforcement learning course with weekly lectures and Jupyter notebook labs
- Stars
- 6.6k
- License
- Unlicense
- Last commit
- Oct 2026
- Last release
- Aug 2020
- Language
- Jupyter Notebook
6,443 on 4 Apr 20266,601 on 31 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Practical_RL is the course material for a reinforcement learning class taught at HSE and YSDA, in English and Russian. It has a weekly syllabus from cross-entropy method and value iteration through DQN, policy gradients, PPO/TRPO, POMDPs and model-based RL. Each week has a seminar notebook, and most weeks have a homework.
Who it is for: Students and engineers learning reinforcement learning through code
Strengths
- Covers tabular methods, DQN, actor-critic, TRPO/PPO, POMDPs and MCTS in one syllabus
- Each major topic has a hands-on seminar notebook, e.g. CartPole, Atari, Taxi
- Runs in Google Colab or locally, and the README links an online-student guide
- Unlicense, so materials can be reused freely
Weaknesses
- Last release was 2020-08-04, and the syllabus references older tools such as OpenAI gym and Taxi-v0
- Lecture slides are hosted externally on Yandex Disk, not in the repository
- README says some assignments use TensorFlow, so framework coverage is mixed
- No LLM or RLHF topics listed in the syllabus
What it needs
- GPU optional
- Docker
- Needs Jupyter, OpenAI Gym, PyTorch, TensorFlow
Quick answers
Is practical_rl open source?
Yes. Its code is on GitHub under the Unlicense license.
Can you run practical_rl with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does practical_rl need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Learning and cookbooks
See all 65| Rank | Project | Score |
|---|---|---|
| 1 | ai-engineering-from-scratchHands-on AI engineering curriculum with 542 lessons across 20 phases | 89 out of 100 |
| 2 | generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript | 81 out of 100 |
| 3 | rag_techniquesCollection of 42 runnable notebooks implementing RAG techniques | 79 out of 100 |
| #4 | cs249r_bookOpen textbook and course materials for machine learning systems engineering | 79 out of 100 |
| #5 | ai-agents-for-beginners18-lesson course on building AI agents with Microsoft Agent Framework | 78 out of 100 |