J. D. Williams

Sample-efficient Deep Reinforcement Learning for Dialog Control

2016 · arXiv (Cornell University)

Representing a dialog policy as a recurrent neural network (RNN) is attractive because it handles partial observability, infers a latent representation of state, and can be optimized with supervised learning (SL) or reinforcement learning (RL). …

The fifth dialog state tracking challenge

2016

Dialog state tracking - the process of updating the dialog state after each interaction with the user - is a key component of most dialog systems. Following a similar scheme to the fourth dialog state …

Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning

2017

End-to-end learning of recurrent neural networks (RNNs) is an attractive solution for dialog systems; however, current techniques are data-intensive and require thousands of dialogs to learn simple behaviors.