@yuwen_lu_: I'm halfway through, damn why did no one ever tell me RL is this fun
Summary
Sanbu 散步 released a modern RL tutorial Hands-On Modern RL, covering from CartPole+PPO basics to LLM post-training (RLHF, DPO, GRPO) and Agentic RL, code-first, English version coming soon.
View Cached Full Text
Cached at: 05/31/26, 07:03 AM
Halfway through, holy crap, why has no one ever told me RL is this fun?
Sanbu 散步 (@sanbuphy): Spent some time writing a RL tutorial, Hands-On Modern RL. The path starts with CartPole + PPO, then moves to LLM post-training (RLHF, DPO, GRPO), and Agentic RL. Code-first, formulas used to explain phenomena. English version coming soon. Currently a draft. RLHF and Agentic RL sections are under local review. PRs, Issues & GPU sponsorship welcome:
Similar Articles
@sheriyuo: The Hands-on Modern RL tutorial everyone has been waiting for is finally available in English PDF download link: https:…
An open-source hands-on modern reinforcement learning course covering from classic control to LLM post-training, RLHF, DPO, GRPO, and agentic RL is now available as a free English PDF download.
@qingke_ai: https://x.com/qingke_ai/status/2071281892964659384
该文章由ROLL团队分享了在终端环境中进行Agentic RL训练时的实践经验，包括环境管理器设计、异步训练管线以及多种模式切换，并对比了RLVR与Agentic RL的本质区别。
@Phoenixyin13: Highly recommend this RL interview question collection! @sheriyuo compiled 35 RL benchmarks covering both Algorithm and Infrastructure, from PPO, GRPO's clip, KL penalty, advantage calculation, to…
Recommend an RL interview question collection compiled by @sheriyuo, covering algorithms and infrastructure such as PPO, GRPO, MoE, vLLM, suitable for LLM RL interview preparation and research.
@duange6099: If you're also looking to get started with Claude Code, I highly recommend bookmarking this collection of resources. Feel free to share your experiences and learn together. 1. Most comprehensive Chinese tutorial (recommended to read first) Covers from installation to hands-on projects https://github.com/shareAI-lab/le…
A Twitter user shared a carefully curated collection of Claude Code learning resources, including Chinese tutorials, command tips, skill libraries, etc., for beginners to get started.
@chengyongru: When I first started learning RL, I studied Mathematical Foundations of Reinforcement Learning by Professor Shiyu Zhao. I think it's a very good introductory tutorial. GitHub link: https://github.com…
A tweet recommends the book 'Mathematical Foundations of Reinforcement Learning' by Shiyu Zhao, providing a GitHub link to the book's source code and slides.