Taylor Dohmen, Noah Topper, George K. Atia, Andre Beckus, Ashutosh Trivedi 0001, Alvaro Velasquez. Inferring Probabilistic Reward Machines from Non-Markovian Reward Signals for Reinforcement Learning. In Akshat Kumar, Sylvie Thiébaux, Pradeep Varakantham, William Yeoh 0001, editors, Proceedings of the Thirty-Second International Conference on Automated Planning and Scheduling, ICAPS 2022, Singapore (virtual), June 13-24, 2022. pages 574-582, AAAI Press, 2022. [doi]
@inproceedings{DohmenTAB0V22,
title = {Inferring Probabilistic Reward Machines from Non-Markovian Reward Signals for Reinforcement Learning},
author = {Taylor Dohmen and Noah Topper and George K. Atia and Andre Beckus and Ashutosh Trivedi 0001 and Alvaro Velasquez},
year = {2022},
url = {https://ojs.aaai.org/index.php/ICAPS/article/view/19844},
researchr = {https://researchr.org/publication/DohmenTAB0V22},
cites = {0},
citedby = {0},
pages = {574-582},
booktitle = {Proceedings of the Thirty-Second International Conference on Automated Planning and Scheduling, ICAPS 2022, Singapore (virtual), June 13-24, 2022},
editor = {Akshat Kumar and Sylvie Thiébaux and Pradeep Varakantham and William Yeoh 0001},
publisher = {AAAI Press},
isbn = {978-1-57735-874-9},
}