@inproceedings{zheng-etal-2024-3s-multimodal,
title = "{MORE}-3{S}:Multimodal-based Offline Reinforcement Learning with Shared Semantic Spaces",
author = "Zheng, Tianyu and
Zhang, Ge and
Qu, Xingwei and
Kuang, Ming and
Huang, Wenhao and
He, Zhaofeng",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1013",
pages = "11593--11604",
abstract = "Drawing upon the intuition that aligning different modalities to the same semantic embedding space would allow models to understand states and actions more easily, we propose a new perspective to the offline reinforcement learning (RL) challenge. More concretely, we transform it into a supervised learning task by integrating multimodal and pre-trained language models. Our approach incorporates state information derived from images and action-related data obtained from text, thereby bolstering RL training performance and promoting long-term strategic thinking. We emphasize the contextual understanding of language and demonstrate how decision-making in RL can benefit from aligning states{'} and actions{'} representation with languages{'} representation. Our method significantly outperforms current baselines as evidenced by evaluations conducted on Atari and OpenAI Gym environments. This contributes to advancing offline RL performance and efficiency while providing a novel perspective on offline RL.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2024-3s-multimodal">
<titleInfo>
<title>MORE-3S:Multimodal-based Offline Reinforcement Learning with Shared Semantic Spaces</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianyu</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ge</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingwei</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Kuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhao</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaofeng</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Drawing upon the intuition that aligning different modalities to the same semantic embedding space would allow models to understand states and actions more easily, we propose a new perspective to the offline reinforcement learning (RL) challenge. More concretely, we transform it into a supervised learning task by integrating multimodal and pre-trained language models. Our approach incorporates state information derived from images and action-related data obtained from text, thereby bolstering RL training performance and promoting long-term strategic thinking. We emphasize the contextual understanding of language and demonstrate how decision-making in RL can benefit from aligning states’ and actions’ representation with languages’ representation. Our method significantly outperforms current baselines as evidenced by evaluations conducted on Atari and OpenAI Gym environments. This contributes to advancing offline RL performance and efficiency while providing a novel perspective on offline RL.</abstract>
<identifier type="citekey">zheng-etal-2024-3s-multimodal</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1013</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11593</start>
<end>11604</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MORE-3S:Multimodal-based Offline Reinforcement Learning with Shared Semantic Spaces
%A Zheng, Tianyu
%A Zhang, Ge
%A Qu, Xingwei
%A Kuang, Ming
%A Huang, Wenhao
%A He, Zhaofeng
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F zheng-etal-2024-3s-multimodal
%X Drawing upon the intuition that aligning different modalities to the same semantic embedding space would allow models to understand states and actions more easily, we propose a new perspective to the offline reinforcement learning (RL) challenge. More concretely, we transform it into a supervised learning task by integrating multimodal and pre-trained language models. Our approach incorporates state information derived from images and action-related data obtained from text, thereby bolstering RL training performance and promoting long-term strategic thinking. We emphasize the contextual understanding of language and demonstrate how decision-making in RL can benefit from aligning states’ and actions’ representation with languages’ representation. Our method significantly outperforms current baselines as evidenced by evaluations conducted on Atari and OpenAI Gym environments. This contributes to advancing offline RL performance and efficiency while providing a novel perspective on offline RL.
%U https://aclanthology.org/2024.lrec-main.1013
%P 11593-11604
Markdown (Informal)
[MORE-3S:Multimodal-based Offline Reinforcement Learning with Shared Semantic Spaces](https://aclanthology.org/2024.lrec-main.1013) (Zheng et al., LREC-COLING 2024)
ACL