Reward Hacking as Equilibrium under Finite Evaluation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Jiacheng, Huang, Jinbin
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Computer Science and Game Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.28063