@inproceedings{wang-etal-2020-task,
title = "Task-Completion Dialogue Policy Learning via {M}onte {C}arlo Tree Search with Dueling Network",
author = "Wang, Sihan and
Zhou, Kaijie and
Lai, Kunfeng and
Shen, Jianping",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.278",
doi = "10.18653/v1/2020.emnlp-main.278",
pages = "3461--3471",
abstract = "We introduce a framework of Monte Carlo Tree Search with Double-q Dueling network (MCTS-DDU) for task-completion dialogue policy learning. Different from the previous deep model-based reinforcement learning methods, which uses background planning and may suffer from low-quality simulated experiences, MCTS-DDU performs decision-time planning based on dialogue state search trees built by Monte Carlo simulations and is robust to the simulation errors. Such idea arises naturally in human behaviors, e.g. predicting others{'} responses and then deciding our own actions. In the simulated movie-ticket booking task, our method outperforms the background planning approaches significantly. We demonstrate the effectiveness of MCTS and the dueling network in detailed ablation studies, and also compare the performance upper bounds of these two planning methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2020-task">
<titleInfo>
<title>Task-Completion Dialogue Policy Learning via Monte Carlo Tree Search with Dueling Network</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sihan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaijie</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kunfeng</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianping</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a framework of Monte Carlo Tree Search with Double-q Dueling network (MCTS-DDU) for task-completion dialogue policy learning. Different from the previous deep model-based reinforcement learning methods, which uses background planning and may suffer from low-quality simulated experiences, MCTS-DDU performs decision-time planning based on dialogue state search trees built by Monte Carlo simulations and is robust to the simulation errors. Such idea arises naturally in human behaviors, e.g. predicting others’ responses and then deciding our own actions. In the simulated movie-ticket booking task, our method outperforms the background planning approaches significantly. We demonstrate the effectiveness of MCTS and the dueling network in detailed ablation studies, and also compare the performance upper bounds of these two planning methods.</abstract>
<identifier type="citekey">wang-etal-2020-task</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.278</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.278</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3461</start>
<end>3471</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Task-Completion Dialogue Policy Learning via Monte Carlo Tree Search with Dueling Network
%A Wang, Sihan
%A Zhou, Kaijie
%A Lai, Kunfeng
%A Shen, Jianping
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F wang-etal-2020-task
%X We introduce a framework of Monte Carlo Tree Search with Double-q Dueling network (MCTS-DDU) for task-completion dialogue policy learning. Different from the previous deep model-based reinforcement learning methods, which uses background planning and may suffer from low-quality simulated experiences, MCTS-DDU performs decision-time planning based on dialogue state search trees built by Monte Carlo simulations and is robust to the simulation errors. Such idea arises naturally in human behaviors, e.g. predicting others’ responses and then deciding our own actions. In the simulated movie-ticket booking task, our method outperforms the background planning approaches significantly. We demonstrate the effectiveness of MCTS and the dueling network in detailed ablation studies, and also compare the performance upper bounds of these two planning methods.
%R 10.18653/v1/2020.emnlp-main.278
%U https://aclanthology.org/2020.emnlp-main.278
%U https://doi.org/10.18653/v1/2020.emnlp-main.278
%P 3461-3471
Markdown (Informal)
[Task-Completion Dialogue Policy Learning via Monte Carlo Tree Search with Dueling Network](https://aclanthology.org/2020.emnlp-main.278) (Wang et al., EMNLP 2020)
ACL