RL study guide — foundations through RLHF, DPO, GRPO, RLVR, agentic RL, and offline RL. Hand-written CS294 notes, 34 lecture drafts, 9 tested exercises, citations that resolve.
Latest release v1.0.0 · 4 Nov 2026
2 files for Codex, OpenCode and Claude Code: Study-Reinforcement-Learning AGENTS.md, Study-Reinforcement-Learning CLAUDE.md — 2,220 tokens loaded in every session.
AGENTS.md A 1,901 tok CLAUDE.md A 319 tok These files are 0bserver07/Study-Reinforcement-Learning's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.