Osbert Bastani, Yewen Pu, Armando Solar-Lezama. Verifiable Reinforcement Learning via Policy Extraction. In Samy Bengio, Hanna M. Wallach, Hugo Larochelle, Kristen Grauman, Nicolò Cesa-Bianchi, Roman Garnett, editors, Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, 3-8 December 2018, Montréal, Canada. pages 2499-2509, 2018. [doi]
@inproceedings{BastaniPS18,
title = {Verifiable Reinforcement Learning via Policy Extraction},
author = {Osbert Bastani and Yewen Pu and Armando Solar-Lezama},
year = {2018},
url = {http://papers.nips.cc/paper/7516-verifiable-reinforcement-learning-via-policy-extraction},
researchr = {https://researchr.org/publication/BastaniPS18},
cites = {0},
citedby = {0},
pages = {2499-2509},
booktitle = {Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, 3-8 December 2018, Montréal, Canada},
editor = {Samy Bengio and Hanna M. Wallach and Hugo Larochelle and Kristen Grauman and Nicolò Cesa-Bianchi and Roman Garnett},
}