Skip to main content
← Choose a different target

Unlock: Reinforcement Learning from Human Feedback

The RLHF pipeline as math, not folklore: Bradley-Terry with sycophancy and intransitivity, KL-shielded PPO with overoptimization mitigation, the DPO implicit-reward identity and its likelihood-displacement failure, online-vs-offline preference learning, Nash-LHF, and the LIMA challenge to whether you need RL at all.

264 Prerequisites0 Mastered0 Working202 Gaps
Prerequisite mastery23%
Recommended probe

Floating-Point Arithmetic is your weakest prerequisite with available questions. You haven't been assessed on this topic yet.

Reinforcement Learning from Human FeedbackTARGET
Floating-Point ArithmeticAxiomsWEAKEST
Not assessed3 questions
Graph Neural NetworksAdvanced
Not assessed4 questions
Numerical Linear AlgebraFoundations
Not assessed1 question
Attention for Protein Structure: AlphaFold and SuccessorsResearch
No quiz
Policy Gradient TheoremAdvanced
Not assessed8 questions
Reward Design and Reward MisspecificationAdvanced
Not assessed1 question
RLHF and AlignmentResearch
Not assessed3 questions
Reinforcement Learning for Synthesis PlanningResearch
No quiz

Sign in to track your mastery and see personalized gap analysis.