All work

06

Study: Reinforcement Learning

Foundations through RLHF, DPO, GRPO, RLVR, agentic RL and offline RL.

Built in
Notes
Status
Public
Since
2026
Source

Hand-written CS294 notes, nineteen lecture drafts, five tested exercises, and citations that resolve.

That last clause is not a boast, it is the bar. A study guide whose references do not resolve is a study guide that has not been checked.