@inproceedings{chaudhury-etal-2021-neuro,
title = "Neuro-Symbolic Approaches for Text-Based Policy Learning",
author = "Chaudhury, Subhajit and
Sen, Prithviraj and
Ono, Masaki and
Kimura, Daiki and
Tatsubori, Michiaki and
Munawar, Asim",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.245",
doi = "10.18653/v1/2021.emnlp-main.245",
pages = "3073--3078",
abstract = "Text-Based Games (TBGs) have emerged as important testbeds for reinforcement learning (RL) in the natural language domain. Previous methods using LSTM-based action policies are uninterpretable and often overfit the training games showing poor performance to unseen test games. We present SymboLic Action policy for Textual Environments (SLATE), that learns interpretable action policy rules from symbolic abstractions of textual observations for improved generalization. We outline a method for end-to-end differentiable symbolic rule learning and show that such symbolic policies outperform previous state-of-the-art methods in text-based RL for the coin collector environment from 5-10x fewer training games. Additionally, our method provides human-understandable policy rules that can be readily verified for their logical consistency and can be easily debugged.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chaudhury-etal-2021-neuro">
<titleInfo>
<title>Neuro-Symbolic Approaches for Text-Based Policy Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Subhajit</namePart>
<namePart type="family">Chaudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prithviraj</namePart>
<namePart type="family">Sen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaki</namePart>
<namePart type="family">Ono</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daiki</namePart>
<namePart type="family">Kimura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michiaki</namePart>
<namePart type="family">Tatsubori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asim</namePart>
<namePart type="family">Munawar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text-Based Games (TBGs) have emerged as important testbeds for reinforcement learning (RL) in the natural language domain. Previous methods using LSTM-based action policies are uninterpretable and often overfit the training games showing poor performance to unseen test games. We present SymboLic Action policy for Textual Environments (SLATE), that learns interpretable action policy rules from symbolic abstractions of textual observations for improved generalization. We outline a method for end-to-end differentiable symbolic rule learning and show that such symbolic policies outperform previous state-of-the-art methods in text-based RL for the coin collector environment from 5-10x fewer training games. Additionally, our method provides human-understandable policy rules that can be readily verified for their logical consistency and can be easily debugged.</abstract>
<identifier type="citekey">chaudhury-etal-2021-neuro</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.245</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.245</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>3073</start>
<end>3078</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neuro-Symbolic Approaches for Text-Based Policy Learning
%A Chaudhury, Subhajit
%A Sen, Prithviraj
%A Ono, Masaki
%A Kimura, Daiki
%A Tatsubori, Michiaki
%A Munawar, Asim
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F chaudhury-etal-2021-neuro
%X Text-Based Games (TBGs) have emerged as important testbeds for reinforcement learning (RL) in the natural language domain. Previous methods using LSTM-based action policies are uninterpretable and often overfit the training games showing poor performance to unseen test games. We present SymboLic Action policy for Textual Environments (SLATE), that learns interpretable action policy rules from symbolic abstractions of textual observations for improved generalization. We outline a method for end-to-end differentiable symbolic rule learning and show that such symbolic policies outperform previous state-of-the-art methods in text-based RL for the coin collector environment from 5-10x fewer training games. Additionally, our method provides human-understandable policy rules that can be readily verified for their logical consistency and can be easily debugged.
%R 10.18653/v1/2021.emnlp-main.245
%U https://aclanthology.org/2021.emnlp-main.245
%U https://doi.org/10.18653/v1/2021.emnlp-main.245
%P 3073-3078
Markdown (Informal)
[Neuro-Symbolic Approaches for Text-Based Policy Learning](https://aclanthology.org/2021.emnlp-main.245) (Chaudhury et al., EMNLP 2021)
ACL
- Subhajit Chaudhury, Prithviraj Sen, Masaki Ono, Daiki Kimura, Michiaki Tatsubori, and Asim Munawar. 2021. Neuro-Symbolic Approaches for Text-Based Policy Learning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3073–3078, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.