Bharat Prakash, Nicholas R. Waytowich, Ashwinkumar Ganesan, Tim Oates, Tinoosh Mohsenin. Guiding Safe Reinforcement Learning Policies Using Structured Language Constraints. In Huáscar Espinoza, José Hernández-Orallo, Xin Cynthia Chen, Seán S. ÓhÉigeartaigh, Xiaowei Huang 0001, Mauricio Castillo-Effen, Richard Mallah, John McDermid, editors, Proceedings of the Workshop on Artificial Intelligence Safety, co-located with 34th AAAI Conference on Artificial Intelligence, SafeAI@AAAI 2020, New York City, NY, USA, February 7, 2020. Volume 2560 of CEUR Workshop Proceedings, pages 153-161, CEUR-WS.org, 2020. [doi]
@inproceedings{PrakashWGOM20,
title = {Guiding Safe Reinforcement Learning Policies Using Structured Language Constraints},
author = {Bharat Prakash and Nicholas R. Waytowich and Ashwinkumar Ganesan and Tim Oates and Tinoosh Mohsenin},
year = {2020},
url = {http://ceur-ws.org/Vol-2560/paper38.pdf},
researchr = {https://researchr.org/publication/PrakashWGOM20},
cites = {0},
citedby = {0},
pages = {153-161},
booktitle = {Proceedings of the Workshop on Artificial Intelligence Safety, co-located with 34th AAAI Conference on Artificial Intelligence, SafeAI@AAAI 2020, New York City, NY, USA, February 7, 2020},
editor = {Huáscar Espinoza and José Hernández-Orallo and Xin Cynthia Chen and Seán S. ÓhÉigeartaigh and Xiaowei Huang 0001 and Mauricio Castillo-Effen and Richard Mallah and John McDermid},
volume = {2560},
series = {CEUR Workshop Proceedings},
publisher = {CEUR-WS.org},
}