Conditionally Combining Robot Skills using Large Language Models

This paper combines two contributions. First, we introduce an extension of the Meta-World benchmark, which we call "Language-World," which allows a large language model to operate in a simulated robotic environment using semi-structured natural language queries and scripted skills describe...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-10
Hauptverfasser: Zentner, K R, Ryan, Julian, Ichter, Brian, Sukhatme, Gaurav S
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Zentner, K R
Ryan, Julian
Ichter, Brian
Sukhatme, Gaurav S
description This paper combines two contributions. First, we introduce an extension of the Meta-World benchmark, which we call "Language-World," which allows a large language model to operate in a simulated robotic environment using semi-structured natural language queries and scripted skills described using natural language. By using the same set of tasks as Meta-World, Language-World results can be easily compared to Meta-World results, allowing for a point of comparison between recent methods using Large Language Models (LLMs) and those using Deep Reinforcement Learning. Second, we introduce a method we call Plan Conditioned Behavioral Cloning (PCBC), that allows finetuning the behavior of high-level plans using end-to-end demonstrations. Using Language-World, we show that PCBC is able to achieve strong performance in a variety of few-shot regimes, often achieving task generalization with as little as a single demonstration. We have made Language-World available as open-source software at https://github.com/krzentner/language-world/.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2882599033</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2882599033</sourcerecordid><originalsourceid>FETCH-proquest_journals_28825990333</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRwcM7PS8ksyczPS8zJqVRwzs9NyszLzEtXCMpPyi9RCM7OzMkpVigtBgn5JBalpwLJvPTSRCDDNz8lNaeYh4E1LTGnOJUXSnMzKLu5hjh76BYU5ReWphaXxGfllxYBTS-ON7KwMDK1tDQwNjYmThUAO685Bw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2882599033</pqid></control><display><type>article</type><title>Conditionally Combining Robot Skills using Large Language Models</title><source>Free E- Journals</source><creator>Zentner, K R ; Ryan, Julian ; Ichter, Brian ; Sukhatme, Gaurav S</creator><creatorcontrib>Zentner, K R ; Ryan, Julian ; Ichter, Brian ; Sukhatme, Gaurav S</creatorcontrib><description>This paper combines two contributions. First, we introduce an extension of the Meta-World benchmark, which we call "Language-World," which allows a large language model to operate in a simulated robotic environment using semi-structured natural language queries and scripted skills described using natural language. By using the same set of tasks as Meta-World, Language-World results can be easily compared to Meta-World results, allowing for a point of comparison between recent methods using Large Language Models (LLMs) and those using Deep Reinforcement Learning. Second, we introduce a method we call Plan Conditioned Behavioral Cloning (PCBC), that allows finetuning the behavior of high-level plans using end-to-end demonstrations. Using Language-World, we show that PCBC is able to achieve strong performance in a variety of few-shot regimes, often achieving task generalization with as little as a single demonstration. We have made Language-World available as open-source software at https://github.com/krzentner/language-world/.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Cloning ; Large language models ; Open source software ; Skills</subject><ispartof>arXiv.org, 2023-10</ispartof><rights>2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>778,782</link.rule.ids></links><search><creatorcontrib>Zentner, K R</creatorcontrib><creatorcontrib>Ryan, Julian</creatorcontrib><creatorcontrib>Ichter, Brian</creatorcontrib><creatorcontrib>Sukhatme, Gaurav S</creatorcontrib><title>Conditionally Combining Robot Skills using Large Language Models</title><title>arXiv.org</title><description>This paper combines two contributions. First, we introduce an extension of the Meta-World benchmark, which we call "Language-World," which allows a large language model to operate in a simulated robotic environment using semi-structured natural language queries and scripted skills described using natural language. By using the same set of tasks as Meta-World, Language-World results can be easily compared to Meta-World results, allowing for a point of comparison between recent methods using Large Language Models (LLMs) and those using Deep Reinforcement Learning. Second, we introduce a method we call Plan Conditioned Behavioral Cloning (PCBC), that allows finetuning the behavior of high-level plans using end-to-end demonstrations. Using Language-World, we show that PCBC is able to achieve strong performance in a variety of few-shot regimes, often achieving task generalization with as little as a single demonstration. We have made Language-World available as open-source software at https://github.com/krzentner/language-world/.</description><subject>Cloning</subject><subject>Large language models</subject><subject>Open source software</subject><subject>Skills</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRwcM7PS8ksyczPS8zJqVRwzs9NyszLzEtXCMpPyi9RCM7OzMkpVigtBgn5JBalpwLJvPTSRCDDNz8lNaeYh4E1LTGnOJUXSnMzKLu5hjh76BYU5ReWphaXxGfllxYBTS-ON7KwMDK1tDQwNjYmThUAO685Bw</recordid><startdate>20231025</startdate><enddate>20231025</enddate><creator>Zentner, K R</creator><creator>Ryan, Julian</creator><creator>Ichter, Brian</creator><creator>Sukhatme, Gaurav S</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20231025</creationdate><title>Conditionally Combining Robot Skills using Large Language Models</title><author>Zentner, K R ; Ryan, Julian ; Ichter, Brian ; Sukhatme, Gaurav S</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28825990333</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Cloning</topic><topic>Large language models</topic><topic>Open source software</topic><topic>Skills</topic><toplevel>online_resources</toplevel><creatorcontrib>Zentner, K R</creatorcontrib><creatorcontrib>Ryan, Julian</creatorcontrib><creatorcontrib>Ichter, Brian</creatorcontrib><creatorcontrib>Sukhatme, Gaurav S</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection (ProQuest)</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zentner, K R</au><au>Ryan, Julian</au><au>Ichter, Brian</au><au>Sukhatme, Gaurav S</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Conditionally Combining Robot Skills using Large Language Models</atitle><jtitle>arXiv.org</jtitle><date>2023-10-25</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>This paper combines two contributions. First, we introduce an extension of the Meta-World benchmark, which we call "Language-World," which allows a large language model to operate in a simulated robotic environment using semi-structured natural language queries and scripted skills described using natural language. By using the same set of tasks as Meta-World, Language-World results can be easily compared to Meta-World results, allowing for a point of comparison between recent methods using Large Language Models (LLMs) and those using Deep Reinforcement Learning. Second, we introduce a method we call Plan Conditioned Behavioral Cloning (PCBC), that allows finetuning the behavior of high-level plans using end-to-end demonstrations. Using Language-World, we show that PCBC is able to achieve strong performance in a variety of few-shot regimes, often achieving task generalization with as little as a single demonstration. We have made Language-World available as open-source software at https://github.com/krzentner/language-world/.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-10
issn 2331-8422
language eng
recordid cdi_proquest_journals_2882599033
source Free E- Journals
subjects Cloning
Large language models
Open source software
Skills
title Conditionally Combining Robot Skills using Large Language Models
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T08%3A25%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Conditionally%20Combining%20Robot%20Skills%20using%20Large%20Language%20Models&rft.jtitle=arXiv.org&rft.au=Zentner,%20K%20R&rft.date=2023-10-25&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2882599033%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2882599033&rft_id=info:pmid/&rfr_iscdi=true