@inproceedings{Milani2025Aligning,
author = {Stephanie Milani and Zhicheng Zhang and Nicholay Topin and Lirong Xia and Fei Fang},
title = {Aligning Agent Policies with Preferences: Human-Centered Interpretable Reinforcement Learning},
booktitle = {AAAI/ACM Conference on AI, Ethics, and Society (AIES)},
year = {2025},
keywords = {reinforcement learning, interpretability, human-centered AI, preference learning, alignment},
abstract = {We propose a framework that interleaves human preference learning with an evolutionary algorithm for training interpretable reinforcement learning policies, aligning agent behavior with human feedback throughout training rather than only after the fact.}
}