most citedEfficient RLHF: Reducing the Memory Usage of PPO

2 citations · 2 across the 1 of their papers we have counts for

collaborators

1 paper

cs.LG2023★ 2 cited

Efficient RLHF: Reducing the Memory Usage of PPO

Michael Santacroce, Yadong Lu, Han Yu +2

Reinforcement Learning with Human Feedback (RLHF) has revolutionized language modeling by aligning models with human preferences. However, the RL stage, Proximal Policy Optimizatio…