Search Results for author:
Found 1 papers, 0 papers with code
Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking
However, even pretrain reward ensembles do not eliminate reward hacking: we show several qualitative reward hacking phenomena that are not mitigated by ensembling because all reward models in the ensemble exhibit similar error patterns.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
