RLHF - 分类 - vllbc02's blogs

RLHF

2025

RLOO 07-15

ReMAX（REINFORCE argmax） 07-15

REINFORECE++ 07-15

Reinforcing General Reasoning without Verifiers 07-15

ppo 07-15

grpo 07-15

dapo 07-15

RLPR：EXTRAPOLATING RLVR TO GENERAL DOMAINS WITHOUT VERIFIERS 07-10

GENERALIST REWARD MODELS：FOUND INSIDE LARGE LANGUAGE MODELS 07-10