alessiodm/drl-zh
An educational Jupyter Notebook course teaching deep reinforcement learning by building algorithms from scratch.
Not currently ranked — collecting fresh signals.
star history
The course starts with MDPs and tabular RL, progressing to DQN, REINFORCE, actor-critic methods, DDPG, TD3, SAC, and PPO. Advanced notebooks cover RLHF with PPO, DPO, and GRPO for language models, Decision Transformers, and world models like Dreamer. Students write code in guided TODO sections with complete solutions provided.
Frequently asked
- What is alessiodm/drl-zh?
- An educational Jupyter Notebook course teaching deep reinforcement learning by building algorithms from scratch.
- Is drl-zh open source?
- Yes — alessiodm/drl-zh is open source, released under the MIT license.
- What language is drl-zh written in?
- alessiodm/drl-zh is primarily written in Jupyter Notebook.
- How popular is drl-zh?
- alessiodm/drl-zh has 2.3k stars on GitHub.
- Where can I find drl-zh?
- alessiodm/drl-zh is on GitHub at https://github.com/alessiodm/drl-zh.