The Trajectory Alignment Coefficient in Two Acts: From Reward Tuning to Reward Learning
Lists
Only you see this
BibTeX
@misc{muslimani2026trajectory,
author = {Calarina Muslimani and Yunshu Du and Kenta Kawamoto and Kaushik Subramanian and Peter Stone and Peter R. Wurman},
title = {{The Trajectory Alignment Coefficient in Two Acts: From Reward Tuning to Reward Learning}},
year = {2026},
eprint = {2601.16906},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2601.16906},
}