@article{dilutednearoptimalexpertdemonstrations, title = {Diluted Near-Optimal Expert Demonstrations for Guiding Dialogue Stochastic Policy Optimisation}, author = {Thibault Cordier and Tanguy Urvoy and Lina M. Rojas-Barahona and Fabrice Lefèvre}, year = {2020}, eprint = {2012.04687}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2012.04687v1}, }