@InProceedings{manuvinakurike-devault-georgila:2017:W17-55,
  author    = {Manuvinakurike, Ramesh  and  DeVault, David  and  Georgila, Kallirroi},
  title     = {Using Reinforcement Learning to Model Incrementality in a Fast-Paced Dialogue Game},
  booktitle = {Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue},
  month     = {August},
  year      = {2017},
  address   = {Saarbrücken, Germany},
  publisher = {Association for Computational Linguistics},
  pages     = {331--341},
  abstract  = {We apply Reinforcement Learning (RL) to the problem of incremental dialogue
	policy learning in the context of a fast-paced dialogue game. We compare the
	policy learned by RL with a high-performance baseline policy which has been
	shown to perform very efficiently (nearly as well as humans) in this dialogue
	game. The RL policy outperforms the baseline policy in offline simulations
	(based on real user data). We provide a detailed comparison of the RL policy
	and the baseline policy, including information about how much effort and time
	it took to develop each one of them. We also highlight the cases where the RL
	policy performs better, and show that understanding the RL policy can provide
	valuable insights which can inform the creation of an even better rule-based
	policy.},
  url       = {http://aclweb.org/anthology/W17-5539}
}