@inproceedings{zhang2019budgeted,
author = {Zhang, Zhirui and Li, Xiujun and Gao, Jianfeng and Chen, Enhong},
title = {Budgeted Policy Learning for Task-Oriented Dialogue Systems},
booktitle = {ACL 2019},
year = {2019},
month = {July},
abstract = {This paper presents a new approach that extends Deep Dyna-Q (DDQ) by incorporating a Budget-Conscious Scheduling (BCS) to best utilize a fixed, small amount of user interactions (budget) for learning task-oriented dialogue agents. BCS consists of (1) a Poisson-based global scheduler to allocate budget over different stages of training; (2) a controller to decide at each training step whether the agent is trained using real or simulated experiences; (3) a user goal sampling module to generate the experiences that are most effective for policy learning. Experiments on a movie-ticket booking task with simulated and real users show that our approach leads to significant improvements in success rate over the state-of-the-art baselines given the fixed budget},
url = {http://approjects.co.za/?big=en-us/research/publication/budgeted-policy-learning-for-task-oriented-dialogue-systems/},
}