@inproceedings{ryu-etal-2022-fire,
title = "Fire Burns, Sword Cuts: Commonsense Inductive Bias for Exploration in Text-based Games",
author = "Ryu, Dongwon and
Shareghi, Ehsan and
Fang, Meng and
Xu, Yunqiu and
Pan, Shirui and
Haf, Reza",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-short.56/",
doi = "10.18653/v1/2022.acl-short.56",
pages = "515--522",
abstract = "Text-based games (TGs) are exciting testbeds for developing deep reinforcement learning techniques due to their partially observed environments and large action spaces. In these games, the agent learns to explore the environment via natural language interactions with the game simulator. A fundamental challenge in TGs is the efficient exploration of the large action space when the agent has not yet acquired enough knowledge about the environment. We propose CommExpl, an exploration technique that injects external commonsense knowledge, via a pretrained language model (LM), into the agent during training when the agent is the most uncertain about its next action. Our method exhibits improvement on the collected game scores during the training in four out of nine games from Jericho. Additionally, the produced trajectory of actions exhibit lower perplexity, when tested with a pretrained LM, indicating better closeness to human language."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ryu-etal-2022-fire">
<titleInfo>
<title>Fire Burns, Sword Cuts: Commonsense Inductive Bias for Exploration in Text-based Games</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongwon</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Shareghi</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">Yunqiu</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shirui</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reza</namePart>
<namePart type="family">Haf</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 2: Short 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 (TGs) are exciting testbeds for developing deep reinforcement learning techniques due to their partially observed environments and large action spaces. In these games, the agent learns to explore the environment via natural language interactions with the game simulator. A fundamental challenge in TGs is the efficient exploration of the large action space when the agent has not yet acquired enough knowledge about the environment. We propose CommExpl, an exploration technique that injects external commonsense knowledge, via a pretrained language model (LM), into the agent during training when the agent is the most uncertain about its next action. Our method exhibits improvement on the collected game scores during the training in four out of nine games from Jericho. Additionally, the produced trajectory of actions exhibit lower perplexity, when tested with a pretrained LM, indicating better closeness to human language.</abstract>
<identifier type="citekey">ryu-etal-2022-fire</identifier>
<identifier type="doi">10.18653/v1/2022.acl-short.56</identifier>
<location>
<url>https://aclanthology.org/2022.acl-short.56/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>515</start>
<end>522</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fire Burns, Sword Cuts: Commonsense Inductive Bias for Exploration in Text-based Games
%A Ryu, Dongwon
%A Shareghi, Ehsan
%A Fang, Meng
%A Xu, Yunqiu
%A Pan, Shirui
%A Haf, Reza
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F ryu-etal-2022-fire
%X Text-based games (TGs) are exciting testbeds for developing deep reinforcement learning techniques due to their partially observed environments and large action spaces. In these games, the agent learns to explore the environment via natural language interactions with the game simulator. A fundamental challenge in TGs is the efficient exploration of the large action space when the agent has not yet acquired enough knowledge about the environment. We propose CommExpl, an exploration technique that injects external commonsense knowledge, via a pretrained language model (LM), into the agent during training when the agent is the most uncertain about its next action. Our method exhibits improvement on the collected game scores during the training in four out of nine games from Jericho. Additionally, the produced trajectory of actions exhibit lower perplexity, when tested with a pretrained LM, indicating better closeness to human language.
%R 10.18653/v1/2022.acl-short.56
%U https://aclanthology.org/2022.acl-short.56/
%U https://doi.org/10.18653/v1/2022.acl-short.56
%P 515-522
Markdown (Informal)
[Fire Burns, Sword Cuts: Commonsense Inductive Bias for Exploration in Text-based Games](https://aclanthology.org/2022.acl-short.56/) (Ryu et al., ACL 2022)
ACL