Hybrid Reinforcement/Supervised Learning of Dialogue Policies from Fixed Data Sets James Henderson author Oliver Lemon author Kallirroi Georgila author 2008 text journal article Computational Linguistics continuing periodical academic journal henderson-etal-2008-hybrid 10.1162/coli.2008.07-028-R2-05-82 https://aclanthology.org/J08-4002/ 2008 34 4 487 511