Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble

Documenti analoghi

• SALMON: Self-Alignment with Instructable Reward Models
  di: Sun, Zhiqing, et al.
  Pubblicazione: (2023)
• Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
  di: Sun, Zhiqing, et al.
  Pubblicazione: (2024)
• Off-Policy Corrected Reward Modeling for Reinforcement Learning from Human Feedback
  di: Ackermann, Johannes, et al.
  Pubblicazione: (2025)
• Parameter Efficient Reinforcement Learning from Human Feedback
  di: Sidahmed, Hakim, et al.
  Pubblicazione: (2024)
• Gradient Regularization Prevents Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards
  di: Ackermann, Johannes, et al.
  Pubblicazione: (2026)