IR$^3$: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking

Documenti analoghi

• Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking
  di: Beigi, Mohammad, et al.
  Pubblicazione: (2026)
• ODIN: Disentangled Reward Mitigates Hacking in RLHF
  di: Chen, Lichang, et al.
  Pubblicazione: (2024)
• Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories
  di: Beigi, Mohammad, et al.
  Pubblicazione: (2025)
• Reward Hacking Mitigation using Verifiable Composite Rewards
  di: Tarek, Mirza Farhan Bin, et al.
  Pubblicazione: (2025)
• Repairing Reward Functions with Feedback to Mitigate Reward Hacking
  di: Hatgis-Kessell, Stephane, et al.
  Pubblicazione: (2025)