Reinforcement Learning of Dialogue Strategies with Hierarchical Abstract Machines

@article{Cuayhuitl2006ReinforcementLO,
  title={Reinforcement Learning of Dialogue Strategies with Hierarchical Abstract Machines},
  author={Heriberto Cuay{\'a}huitl and Steve Renals and Oliver Lemon and Hiroshi Shimodaira},
  journal={2006 IEEE Spoken Language Technology Workshop},
  year={2006},
  pages={182-185}
}
In this paper we propose partially specified dialogue strategies for dialogue strategy optimization, where part of the strategy is specified deterministically and the rest optimized with reinforcement learning (RL). To do this we apply RL with hierarchical abstract machines (HAMs). We also propose to build simulated users using HAMs, incorporating a combination of hierarchical deterministic and probabilistic behaviour. We performed experiments using a single-goal flight booking dialogue system… CONTINUE READING

Similar Papers

Loading similar papers…