Gradient Regularization Prevents Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards

Documenti analoghi

• Off-Policy Corrected Reward Modeling for Reinforcement Learning from Human Feedback
  di: Ackermann, Johannes, et al.
  Pubblicazione: (2025)
• Mitigating Reward Hacking in RLHF via Advantage Sign Robustness
  di: Ono, Shinnosuke, et al.
  Pubblicazione: (2026)
• Towards Scalable Oversight via Partitioned Human Supervision
  di: Yin, Ren, et al.
  Pubblicazione: (2025)
• Reward Shaping to Mitigate Reward Hacking in RLHF
  di: Fu, Jiayi, et al.
  Pubblicazione: (2025)
• Feedback Loops With Language Models Drive In-Context Reward Hacking
  di: Pan, Alexander, et al.
  Pubblicazione: (2024)