Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning. (arXiv:1606.02560v1 [cs.AI])

This paper presents an end-to-end framework for task-oriented dialog systems using a variant of Deep Recurrent Q-Networks (DRQN). The model is able to interface with a relational database and jointly learn policies for both language understanding and dialog strategy. Moreover, we propose a hybrid algorithm that combines the strength of reinforcement learning and supervised learning to achieve faster learning speed. We evaluated the proposed model on a 20 Question Game conversational game simulator. Results show that the proposed method outperforms the modular-based baseline and learns a distributed representation of the latent dialog state.

from cs.AI updates on arXiv.org http://ift.tt/1rdPnej
via IFTTT