Learning to control from expert demonstrations
In this paper, we revisit the problem of learning a stabilizing controller from a finite number of demonstrations by an expert. By first focusing on feedback linearizable systems, we show how to combine expert demonstrations into a stabilizing controller, provided that demonstrations are sufficientl...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2022-03 |
|---|---|
| Hauptverfasser: | , , , |
| 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 | Sultangazin, Alimzhan Pannocchi, Luigi Fraile, Lucas Tabuada, Paulo |
| description | In this paper, we revisit the problem of learning a stabilizing controller from a finite number of demonstrations by an expert. By first focusing on feedback linearizable systems, we show how to combine expert demonstrations into a stabilizing controller, provided that demonstrations are sufficiently long and there are at least \(n+1\) of them, where \(n\) is the number of states of the system being controlled. When we have more than \(n+1\) demonstrations, we discuss how to optimally choose the best \(n+1\) demonstrations to construct the stabilizing controller. We then extend these results to a class of systems that can be embedded into a higher-dimensional system containing a chain of integrators. The feasibility of the proposed algorithm is demonstrated by applying it on a CrazyFlie 2.0 quadrotor. |
| format | Article |
| fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2638172507</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2638172507</sourcerecordid><originalsourceid>FETCH-proquest_journals_26381725073</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQ80lNLMrLzEtXKMlXSM7PKynKz1FIK8rPVUitKEgtKlFISc3NzysuKUosyQTSPAysaYk5xam8UJqbQdnNNcTZQ7egKL-wNLW4JD4rv7QoDygVb2RmbGEItMXA3Jg4VQA4QDL_</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2638172507</pqid></control><display><type>article</type><title>Learning to control from expert demonstrations</title><source>Free E- Journals</source><creator>Sultangazin, Alimzhan ; Pannocchi, Luigi ; Fraile, Lucas ; Tabuada, Paulo</creator><creatorcontrib>Sultangazin, Alimzhan ; Pannocchi, Luigi ; Fraile, Lucas ; Tabuada, Paulo</creatorcontrib><description>In this paper, we revisit the problem of learning a stabilizing controller from a finite number of demonstrations by an expert. By first focusing on feedback linearizable systems, we show how to combine expert demonstrations into a stabilizing controller, provided that demonstrations are sufficiently long and there are at least \(n+1\) of them, where \(n\) is the number of states of the system being controlled. When we have more than \(n+1\) demonstrations, we discuss how to optimally choose the best \(n+1\) demonstrations to construct the stabilizing controller. We then extend these results to a class of systems that can be embedded into a higher-dimensional system containing a chain of integrators. The feasibility of the proposed algorithm is demonstrated by applying it on a CrazyFlie 2.0 quadrotor.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Controllers ; Integrators ; Learning</subject><ispartof>arXiv.org, 2022-03</ispartof><rights>2022. 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>776,780</link.rule.ids></links><search><creatorcontrib>Sultangazin, Alimzhan</creatorcontrib><creatorcontrib>Pannocchi, Luigi</creatorcontrib><creatorcontrib>Fraile, Lucas</creatorcontrib><creatorcontrib>Tabuada, Paulo</creatorcontrib><title>Learning to control from expert demonstrations</title><title>arXiv.org</title><description>In this paper, we revisit the problem of learning a stabilizing controller from a finite number of demonstrations by an expert. By first focusing on feedback linearizable systems, we show how to combine expert demonstrations into a stabilizing controller, provided that demonstrations are sufficiently long and there are at least \(n+1\) of them, where \(n\) is the number of states of the system being controlled. When we have more than \(n+1\) demonstrations, we discuss how to optimally choose the best \(n+1\) demonstrations to construct the stabilizing controller. We then extend these results to a class of systems that can be embedded into a higher-dimensional system containing a chain of integrators. The feasibility of the proposed algorithm is demonstrated by applying it on a CrazyFlie 2.0 quadrotor.</description><subject>Algorithms</subject><subject>Controllers</subject><subject>Integrators</subject><subject>Learning</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQ80lNLMrLzEtXKMlXSM7PKynKz1FIK8rPVUitKEgtKlFISc3NzysuKUosyQTSPAysaYk5xam8UJqbQdnNNcTZQ7egKL-wNLW4JD4rv7QoDygVb2RmbGEItMXA3Jg4VQA4QDL_</recordid><startdate>20220317</startdate><enddate>20220317</enddate><creator>Sultangazin, Alimzhan</creator><creator>Pannocchi, Luigi</creator><creator>Fraile, Lucas</creator><creator>Tabuada, Paulo</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>20220317</creationdate><title>Learning to control from expert demonstrations</title><author>Sultangazin, Alimzhan ; Pannocchi, Luigi ; Fraile, Lucas ; Tabuada, Paulo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_26381725073</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Algorithms</topic><topic>Controllers</topic><topic>Integrators</topic><topic>Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Sultangazin, Alimzhan</creatorcontrib><creatorcontrib>Pannocchi, Luigi</creatorcontrib><creatorcontrib>Fraile, Lucas</creatorcontrib><creatorcontrib>Tabuada, Paulo</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & 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</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>Sultangazin, Alimzhan</au><au>Pannocchi, Luigi</au><au>Fraile, Lucas</au><au>Tabuada, Paulo</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Learning to control from expert demonstrations</atitle><jtitle>arXiv.org</jtitle><date>2022-03-17</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>In this paper, we revisit the problem of learning a stabilizing controller from a finite number of demonstrations by an expert. By first focusing on feedback linearizable systems, we show how to combine expert demonstrations into a stabilizing controller, provided that demonstrations are sufficiently long and there are at least \(n+1\) of them, where \(n\) is the number of states of the system being controlled. When we have more than \(n+1\) demonstrations, we discuss how to optimally choose the best \(n+1\) demonstrations to construct the stabilizing controller. We then extend these results to a class of systems that can be embedded into a higher-dimensional system containing a chain of integrators. The feasibility of the proposed algorithm is demonstrated by applying it on a CrazyFlie 2.0 quadrotor.</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, 2022-03 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_proquest_journals_2638172507 |
| source | Free E- Journals |
| subjects | Algorithms Controllers Integrators Learning |
| title | Learning to control from expert demonstrations |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T14%3A38%3A54IST&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=Learning%20to%20control%20from%20expert%20demonstrations&rft.jtitle=arXiv.org&rft.au=Sultangazin,%20Alimzhan&rft.date=2022-03-17&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2638172507%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2638172507&rft_id=info:pmid/&rfr_iscdi=true |