Tag

Reinforcement Learning from Human Feedback

Posts and notes tagged with Reinforcement Learning from Human Feedback.

March 21, 202627 min read
Reinforcement Learning from Human Feedback (RLHF)
How Reinforcement Learning from Human Feedback (RLHF) trains language models from human preferences: collecting comparisons, training a reward model, and optimizing the model with PPO under a KL penalty. Part 4 of a series on policy optimization for LLMs.
Machine Learning RLHF Reinforcement Learning from Human Feedback LLM Alignment

Reinforcement Learning from Human Feedback (RLHF)