Niranjani Prasad, Barbara E. Engelhardt, Finale Doshi-Velez. Defining admissible rewards for high-confidence policy evaluation in batch reinforcement learning. In Marzyeh Ghassemi, editor, ACM CHIL '20: ACM Conference on Health, Inference, and Learning, Toronto, Ontario, Canada, April 2-4, 2020 [delayed]. pages 1-9, ACM, 2020. [doi]
@inproceedings{PrasadED20,
title = {Defining admissible rewards for high-confidence policy evaluation in batch reinforcement learning},
author = {Niranjani Prasad and Barbara E. Engelhardt and Finale Doshi-Velez},
year = {2020},
doi = {10.1145/3368555.3384450},
url = {https://doi.org/10.1145/3368555.3384450},
researchr = {https://researchr.org/publication/PrasadED20},
cites = {0},
citedby = {0},
pages = {1-9},
booktitle = {ACM CHIL '20: ACM Conference on Health, Inference, and Learning, Toronto, Ontario, Canada, April 2-4, 2020 [delayed]},
editor = {Marzyeh Ghassemi},
publisher = {ACM},
isbn = {978-1-4503-7046-2},
}