@inproceedings{cao-etal-2020-adaptive,
title = "Adaptive Dialog Policy Learning with Hindsight and User Modeling",
author = "Cao, Yan and
Lu, Keting and
Chen, Xiaoping and
Zhang, Shiqi",
editor = "Pietquin, Olivier and
Muresan, Smaranda and
Chen, Vivian and
Kennington, Casey and
Vandyke, David and
Dethlefs, Nina and
Inoue, Koji and
Ekstedt, Erik and
Ultes, Stefan",
booktitle = "Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = jul,
year = "2020",
address = "1st virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.sigdial-1.40",
doi = "10.18653/v1/2020.sigdial-1.40",
pages = "329--338",
abstract = "Reinforcement learning (RL) methods have been widely used for learning dialog policies. Sample efficiency, i.e., the efficiency of learning from limited dialog experience, is particularly important in RL-based dialog policy learning, because interacting with people is costly and low-quality dialog policies produce very poor user experience. In this paper, we develop LHUA (Learning with Hindsight, User modeling, and Adaptation) that, for the first time, enables dialog agents to adaptively learn with hindsight from both simulated and real users. Simulation and hindsight provide the dialog agent with more experience and more (positive) reinforcement respectively. Experimental results suggest that LHUA outperforms competitive baselines from the literature, including its no-simulation, no-adaptation, and no-hindsight counterparts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cao-etal-2020-adaptive">
<titleInfo>
<title>Adaptive Dialog Policy Learning with Hindsight and User Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keting</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoping</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiqi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Pietquin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivian</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Casey</namePart>
<namePart type="family">Kennington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Vandyke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Dethlefs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koji</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Ekstedt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Ultes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">1st virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Reinforcement learning (RL) methods have been widely used for learning dialog policies. Sample efficiency, i.e., the efficiency of learning from limited dialog experience, is particularly important in RL-based dialog policy learning, because interacting with people is costly and low-quality dialog policies produce very poor user experience. In this paper, we develop LHUA (Learning with Hindsight, User modeling, and Adaptation) that, for the first time, enables dialog agents to adaptively learn with hindsight from both simulated and real users. Simulation and hindsight provide the dialog agent with more experience and more (positive) reinforcement respectively. Experimental results suggest that LHUA outperforms competitive baselines from the literature, including its no-simulation, no-adaptation, and no-hindsight counterparts.</abstract>
<identifier type="citekey">cao-etal-2020-adaptive</identifier>
<identifier type="doi">10.18653/v1/2020.sigdial-1.40</identifier>
<location>
<url>https://aclanthology.org/2020.sigdial-1.40</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>329</start>
<end>338</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adaptive Dialog Policy Learning with Hindsight and User Modeling
%A Cao, Yan
%A Lu, Keting
%A Chen, Xiaoping
%A Zhang, Shiqi
%Y Pietquin, Olivier
%Y Muresan, Smaranda
%Y Chen, Vivian
%Y Kennington, Casey
%Y Vandyke, David
%Y Dethlefs, Nina
%Y Inoue, Koji
%Y Ekstedt, Erik
%Y Ultes, Stefan
%S Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2020
%8 July
%I Association for Computational Linguistics
%C 1st virtual meeting
%F cao-etal-2020-adaptive
%X Reinforcement learning (RL) methods have been widely used for learning dialog policies. Sample efficiency, i.e., the efficiency of learning from limited dialog experience, is particularly important in RL-based dialog policy learning, because interacting with people is costly and low-quality dialog policies produce very poor user experience. In this paper, we develop LHUA (Learning with Hindsight, User modeling, and Adaptation) that, for the first time, enables dialog agents to adaptively learn with hindsight from both simulated and real users. Simulation and hindsight provide the dialog agent with more experience and more (positive) reinforcement respectively. Experimental results suggest that LHUA outperforms competitive baselines from the literature, including its no-simulation, no-adaptation, and no-hindsight counterparts.
%R 10.18653/v1/2020.sigdial-1.40
%U https://aclanthology.org/2020.sigdial-1.40
%U https://doi.org/10.18653/v1/2020.sigdial-1.40
%P 329-338
Markdown (Informal)
[Adaptive Dialog Policy Learning with Hindsight and User Modeling](https://aclanthology.org/2020.sigdial-1.40) (Cao et al., SIGDIAL 2020)
ACL