In the context of offline reinforcement learning with human feedback (RLHF), an ε-fraction of trajectory pairs in a dataset can be corrupted, representing either adversarial attacks or noisy human preferences.

Authors

• Person: Samuel Tesfazgi, Leonhard Sprandl, Sandra Hirche Organization: AISTATS
  Track: Poster Session 3 - aistats 2026

Sources

• Track: Poster Session 3 - aistats 2026 virtual.aistats.org Samuel Tesfazgi, Leonhard Sprandl, Sandra Hirche · AISTATS via serper

Referenced by nodes (1)

• adversarial attack concept