Curriculum Learning Based on Reward Sparseness for Deep Reinforcement Learning of Task Completion Dialogue Management

Curriculum Learning Based on Reward Sparseness for Deep Reinforcement Learning of Task Completion Dialogue Management Atsushi Saito author 2018-10 text Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI Aleksandr Chuklin editor Jeff Dalton editor Julia Kiseleva editor Alexey Borisov editor Mikhail Burtsev editor Association for Computational Linguistics Brussels, Belgium conference publication saito-2018-curriculum 10.18653/v1/W18-5707 https://aclanthology.org/W18-5707/ 2018-10 46 51