opendilab/awesome-RLHF

Organizes research papers, codebases, datasets, and blogs spanning foundational RLHF techniques (Inverse Reinforcement Learning, Apprenticeship Learning, Interactive Machine Learning) through modern LLM alignment applications. Tracks papers chronologically from 2020-present with structured metadata including authors, keywords, code repositories, and experimental environments, enabling systematic tracking of RLHF research frontiers.

4,325 stars.