@inproceedings{nondelusionalqlearningandvalueiteration, title = {Non-delusional Q-learning and value-iteration}, author = {Tyler Lu and Dale Schuurmans and Craig Boutilier}, year = {2018}, booktitle = {NeurIPS 2018 12}, url = {http://papers.nips.cc/paper/8200-non-delusional-q-learning-and-value-iteration}, }