@article{xu2020meta,
author = {Xu, Yumo and Zhu, Chenguang and Peng, Baolin and Zeng, Michael},
title = {Meta Dialogue Policy Learning},
year = {2020},
month = {June},
abstract = {Dialog policy determines the next-step actions for agents and hence is central to a dialogue system. However, when migrated to novel domains with little data, a policy model can fail to adapt due to insufficient interactions with the new environment. We propose Deep Transferable Q-Network (DTQN) to utilize shareable low-level signals between domains, such as dialogue acts and slots. We decompose the state and action representation space into feature subspaces corresponding to these low-level components to facilitate cross-domain knowledge transfer. Furthermore, we embed DTQN in a meta-learning framework and introduce Meta-DTQN with a dual-replay mechanism to enable effective off-policy training and adaptation. In experiments, our model outperforms baseline models in terms of both success rate and dialogue efficiency on the multi-domain dialogue dataset MultiWOZ 2.0.},
url = {http://approjects.co.za/?big=en-us/research/publication/meta-dialogue-policy-learning/},
journal = {arxiv 2006.02588},
}