IR3: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking
Lists
Only you see this
BibTeX
@misc{beigi2026ir,
author = {Mohammad Beigi and Ming Jin and Junshan Zhang and Jiaxin Zhang and Qifan Wang and Lifu Huang},
title = {{IR3: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking}},
year = {2026},
eprint = {2602.19416},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2602.19416},
}Loading related content...