A Survey of Reinforcement Learning from Human Feedback
Open Problems and Fundamental Limitations of Reinforcement...
RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
Secrets of RLHF in Large Language Models Part I: PPO
Secrets of RLHF in Large Language Models Part II: Reward Modeling
RLHF Deciphered: A Critical Analysis of Reinforcement Learning...
Towards Understanding the Influence of Reward Margin on Preference...
Safe RLHF: Safe Reinforcement Learning from Human Feedback
Mitigating Reward Hacking via Information-Theoretic Reward Modeling
MaxMin-RLHF: Towards Equitable Alignment of Large Language Models...
Nash Learning from Human Feedback
Distributional Preference Learning: Understanding and Accounting...
Based on the previous paper:
Crowd-PrefRL: Preference-Based Reward Learning from Crowds
Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct...
Provable Multi-Party Reinforcement Learning with Diverse Human Feedback