<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2022-perceiving">
    <titleInfo>
        <title>Perceiving the World: Question-guided Reinforcement Learning for Text-based Games</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yunqiu</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Meng</namePart>
        <namePart type="family">Fang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ling</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yali</namePart>
        <namePart type="family">Du</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Joey</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chengqi</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <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">Preslav</namePart>
            <namePart type="family">Nakov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aline</namePart>
            <namePart type="family">Villavicencio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dublin, Ireland</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Text-based games provide an interactive way to study natural language processing. While deep reinforcement learning has shown effectiveness in developing the game playing agent, the low sample efficiency and the large action space remain to be the two major challenges that hinder the DRL from being applied in the real world. In this paper, we address the challenges by introducing world-perceiving modules, which automatically decompose tasks and prune actions by answering questions about the environment. We then propose a two-phase training framework to decouple language learning from reinforcement learning, which further improves the sample efficiency. The experimental results show that the proposed method significantly improves the performance and sample efficiency. Besides, it shows robustness against compound error and limited pre-training data.</abstract>
    <identifier type="citekey">xu-etal-2022-perceiving</identifier>
    <identifier type="doi">10.18653/v1/2022.acl-long.41</identifier>
    <location>
        <url>https://aclanthology.org/2022.acl-long.41</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>538</start>
            <end>560</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Perceiving the World: Question-guided Reinforcement Learning for Text-based Games
%A Xu, Yunqiu
%A Fang, Meng
%A Chen, Ling
%A Du, Yali
%A Zhou, Joey
%A Zhang, Chengqi
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F xu-etal-2022-perceiving
%X Text-based games provide an interactive way to study natural language processing. While deep reinforcement learning has shown effectiveness in developing the game playing agent, the low sample efficiency and the large action space remain to be the two major challenges that hinder the DRL from being applied in the real world. In this paper, we address the challenges by introducing world-perceiving modules, which automatically decompose tasks and prune actions by answering questions about the environment. We then propose a two-phase training framework to decouple language learning from reinforcement learning, which further improves the sample efficiency. The experimental results show that the proposed method significantly improves the performance and sample efficiency. Besides, it shows robustness against compound error and limited pre-training data.
%R 10.18653/v1/2022.acl-long.41
%U https://aclanthology.org/2022.acl-long.41
%U https://doi.org/10.18653/v1/2022.acl-long.41
%P 538-560

Markdown (Informal)

[Perceiving the World: Question-guided Reinforcement Learning for Text-based Games](https://aclanthology.org/2022.acl-long.41) (Xu et al., ACL 2022)

• Perceiving the World: Question-guided Reinforcement Learning for Text-based Games (Xu et al., ACL 2022)

ACL

• Yunqiu Xu, Meng Fang, Ling Chen, Yali Du, Joey Zhou, and Chengqi Zhang. 2022. Perceiving the World: Question-guided Reinforcement Learning for Text-based Games. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 538–560, Dublin, Ireland. Association for Computational Linguistics.