... Association for Computational Linguistics:shortpapers, pages 654–659,Portland, Oregon, June 19-24, 2011.c2011 Association for Computational LinguisticsHierarchical Reinforcement Learning and Hidden ... consis-tency (Halliday and Hasan, 1976), and variation,which influence people’s assessment of discourse(Levelt and Kelter, 1982) and generated output (Belz and Reiter, 2006; Foster and Oberlander, 2006).Also, ... content selection. We suggest touse Hierarchical Reinforcement Learning (HRL) toachieve this. Reinforcement Learning (RL) is an at-tractive framework for optimising a sequence of de-cisions given...