ConceptAI & ML
RLHF
Trying to approximate a complex distribution by squashing specific parts according to human preference.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
2Each in their own terms, from the easiest level.
Andrej Karpathy
Reinforcement learning from human feedback models used as assistant models.
Lectures that assume it
4Connections
14The lectures that define it or assume it, and the concepts next to it.
Concepts8
- Language model
- Machine learning
- Reinforcement learning
- Direct preference optimization
- Discriminator - generator gap
- Hallucinations
Show 2 moreShow fewer
Lectures6
- State of GPT: Pretraining, SFT, Reward Modeling & RLHF Pipeline
- Aligning Open Language Models
- Deep Dive into Large Language Models: Pretraining to RLHF
- A Hacker's Guide to Language Models
- What Humans Want: Models of Preference and Reward in Minds and Machines
- Reinforcement Learning from Human Feedback: Algorithms & Applications