Ming Shi 0003, Yingbin Liang, Ness B. Shroff. Reinforcement Learning With Partial Online State Information in POMDPs: Regret Bounds and Limits. IEEE Transactions on Information Theory, 72(7):4895-4925, July 2026. [doi]
@article{ShiLS26,
title = {Reinforcement Learning With Partial Online State Information in POMDPs: Regret Bounds and Limits},
author = {Ming Shi 0003 and Yingbin Liang and Ness B. Shroff},
year = {2026},
month = {July},
doi = {10.1109/TIT.2026.3694700},
url = {https://doi.org/10.1109/TIT.2026.3694700},
researchr = {https://researchr.org/publication/ShiLS26},
cites = {0},
citedby = {0},
journal = {IEEE Transactions on Information Theory},
volume = {72},
number = {7},
pages = {4895-4925},
}