<?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>
        <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
%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)

• To Combine or Not To Combine? A Rainbow Deep Reinforcement Learning Agent for Dialog Policies (Väth & Vu, SIGDIAL 2019)

ACL

• Dirk Väth and Ngoc Thang Vu. 2019. To Combine or Not To Combine? A Rainbow Deep Reinforcement Learning Agent for Dialog Policies. In Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue, pages 62–67, Stockholm, Sweden. Association for Computational Linguistics.