Safe Reward Learning from Human Preferences and Justifications

Ilias Kazantzidis, Timothy J. Norman, Yali Du, Christopher Freeman2026 · DOI

BibTeX
@misc{kazantzidis2026safe,
  author = {Ilias Kazantzidis and Timothy J. Norman and Yali Du and Christopher Freeman},
  title = {{Safe Reward Learning from Human Preferences and Justifications}},
  year = {2026},
  doi = {10.5220/0014408700004052},
}
Figure