To Combine or Not To Combine? A Rainbow Deep Reinforcement Learning Agent for Dialog Policies

To Combine or Not To Combine? A Rainbow Deep Reinforcement Learning Agent for Dialog Policies Dirk Väth author Ngoc Thang Vu author 2019-09 text Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue Satoshi Nakamura editor Milica Gasic editor Ingrid Zukerman editor Gabriel Skantze editor Mikio Nakano editor Alexandros Papangelis editor Stefan Ultes editor Koichiro Yoshino editor Association for Computational Linguistics Stockholm, Sweden conference publication vath-vu-2019-combine 10.18653/v1/W19-5908 https://aclanthology.org/W19-5908/ 2019-09 62 67