@inproceedings{vath-vu-2019-combine,
title = "To Combine or Not To Combine? A Rainbow Deep Reinforcement Learning Agent for Dialog Policies",
author = {V{\"a}th, Dirk and
Vu, Ngoc Thang},
editor = "Nakamura, Satoshi and
Gasic, Milica and
Zukerman, Ingrid and
Skantze, Gabriel and
Nakano, Mikio and
Papangelis, Alexandros and
Ultes, Stefan and
Yoshino, Koichiro",
booktitle = "Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue",
month = sep,
year = "2019",
address = "Stockholm, Sweden",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5908",
doi = "10.18653/v1/W19-5908",
pages = "62--67",
abstract = "In this paper, we explore state-of-the-art deep reinforcement learning methods for dialog policy training such as prioritized experience replay, double deep Q-Networks, dueling network architectures and distributional learning. Our main findings show that each individual method improves the rewards and the task success rate but combining these methods in a Rainbow agent, which performs best across tasks and environments, is a non-trivial task. We, therefore, provide insights about the influence of each method on the combination and how to combine them to form a Rainbow agent.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vath-vu-2019-combine">
<titleInfo>
<title>To Combine or Not To Combine? A Rainbow Deep Reinforcement Learning Agent for Dialog Policies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Väth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ngoc</namePart>
<namePart type="given">Thang</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Nakamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milica</namePart>
<namePart type="family">Gasic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ingrid</namePart>
<namePart type="family">Zukerman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Skantze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikio</namePart>
<namePart type="family">Nakano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandros</namePart>
<namePart type="family">Papangelis</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>
<name type="personal">
<namePart type="given">Koichiro</namePart>
<namePart type="family">Yoshino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Stockholm, Sweden</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we explore state-of-the-art deep reinforcement learning methods for dialog policy training such as prioritized experience replay, double deep Q-Networks, dueling network architectures and distributional learning. Our main findings show that each individual method improves the rewards and the task success rate but combining these methods in a Rainbow agent, which performs best across tasks and environments, is a non-trivial task. We, therefore, provide insights about the influence of each method on the combination and how to combine them to form a Rainbow agent.</abstract>
<identifier type="citekey">vath-vu-2019-combine</identifier>
<identifier type="doi">10.18653/v1/W19-5908</identifier>
<location>
<url>https://aclanthology.org/W19-5908</url>
</location>
<part>
<date>2019-09</date>
<extent unit="page">
<start>62</start>
<end>67</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T To Combine or Not To Combine? A Rainbow Deep Reinforcement Learning Agent for Dialog Policies
%A Väth, Dirk
%A Vu, Ngoc Thang
%Y Nakamura, Satoshi
%Y Gasic, Milica
%Y Zukerman, Ingrid
%Y Skantze, Gabriel
%Y Nakano, Mikio
%Y Papangelis, Alexandros
%Y Ultes, Stefan
%Y Yoshino, Koichiro
%S Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue
%D 2019
%8 September
%I Association for Computational Linguistics
%C Stockholm, Sweden
%F vath-vu-2019-combine
%X In this paper, we explore state-of-the-art deep reinforcement learning methods for dialog policy training such as prioritized experience replay, double deep Q-Networks, dueling network architectures and distributional learning. Our main findings show that each individual method improves the rewards and the task success rate but combining these methods in a Rainbow agent, which performs best across tasks and environments, is a non-trivial task. We, therefore, provide insights about the influence of each method on the combination and how to combine them to form a Rainbow agent.
%R 10.18653/v1/W19-5908
%U https://aclanthology.org/W19-5908
%U https://doi.org/10.18653/v1/W19-5908
%P 62-67
Markdown (Informal)
[To Combine or Not To Combine? A Rainbow Deep Reinforcement Learning Agent for Dialog Policies](https://aclanthology.org/W19-5908) (Väth & Vu, SIGDIAL 2019)
ACL