Efficient Dialog Policy Learning by Reasoning with Contextual Knowledge


  • Haodi Zhang Shenzhen University
  • Zhichao Zeng Shenzhen University
  • Keting Lu Baidu.com,Inc
  • Kaishun Wu Shenzhen University
  • Shiqi Zhang SUNY Binghamton




Speech & Natural Language Processing (SNLP)


Goal-oriented dialog policy learning algorithms aim to learn a dialog policy for selecting language actions based on the current dialog state. Deep reinforcement learning methods have been used for dialog policy learning. This work is motivated by the observation that, although dialog is a domain with rich contextual knowledge, reinforcement learning methods are ill-equipped to incorporate such knowledge into the dialog policy learning process. In this paper, we develop a deep reinforcement learning framework for goal-oriented dialog policy learning that learns user preferences from user goal data, while leveraging commonsense knowledge from people. The developed framework has been evaluated using a realistic dialog simulation platform. Compared with baselines from the literature and the ablations of our approach, we see significant improvements in learning efficiency and the quality of the computed action policies.




How to Cite

Zhang, H., Zeng, Z., Lu, K., Wu, K., & Zhang, S. (2022). Efficient Dialog Policy Learning by Reasoning with Contextual Knowledge. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10), 11667-11675. https://doi.org/10.1609/aaai.v36i10.21421



AAAI Technical Track on Speech and Natural Language Processing