Improving a Proportional Integral Controller with Reinforcement Learning on a Throttle Valve Benchmark
This paper presents a learning-based control strategy for non-linear throttle valves with an asymmetric hysteresis, leading to a near-optimal controller without requiring any prior knowledge about the environment. We start with a carefully tuned Proportional Integrator (PI) controller and exploit th...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2024-07 |
---|---|
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 | Daoudi, Paul Mavkov, Bojan Robu, Bogdan Prieur, Christophe Witrant, Emmanuel Barlier, Merwan Ludovic Dos Santos |
description | This paper presents a learning-based control strategy for non-linear throttle valves with an asymmetric hysteresis, leading to a near-optimal controller without requiring any prior knowledge about the environment. We start with a carefully tuned Proportional Integrator (PI) controller and exploit the recent advances in Reinforcement Learning (RL) with Guides to improve the closed-loop behavior by learning from the additional interactions with the valve. We test the proposed control method in various scenarios on three different valves, all highlighting the benefits of combining both PI and RL frameworks to improve control performance in non-linear stochastic systems. In all the experimental test cases, the resulting agent has a better sample efficiency than traditional RL agents and outperforms the PI controller. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2930079057</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2930079057</sourcerecordid><originalsourceid>FETCH-proquest_journals_29300790573</originalsourceid><addsrcrecordid>eNqNjcEKwjAQRIMgWLT_EPBciIm19qooCh5ExGsJZWur6a5uUv19K_gBnmYO8-YNRKSNmSXLudYjEXt_U0rpRabT1ESi2rcPpleDV2nlkelBHBpC6-QeA1y5L2vCwOQcsHw3oZYnaLAiLqEFDPIAlvGLE_YP55opBAfyYt0L5AqwrFvL94kYVtZ5iH85FtPt5rzeJb382YEPxY067rW-0LlRKstVmpn_Vh8RxkeY</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2930079057</pqid></control><display><type>article</type><title>Improving a Proportional Integral Controller with Reinforcement Learning on a Throttle Valve Benchmark</title><source>Free E- Journals</source><creator>Daoudi, Paul ; Mavkov, Bojan ; Robu, Bogdan ; Prieur, Christophe ; Witrant, Emmanuel ; Barlier, Merwan ; Ludovic Dos Santos</creator><creatorcontrib>Daoudi, Paul ; Mavkov, Bojan ; Robu, Bogdan ; Prieur, Christophe ; Witrant, Emmanuel ; Barlier, Merwan ; Ludovic Dos Santos</creatorcontrib><description>This paper presents a learning-based control strategy for non-linear throttle valves with an asymmetric hysteresis, leading to a near-optimal controller without requiring any prior knowledge about the environment. We start with a carefully tuned Proportional Integrator (PI) controller and exploit the recent advances in Reinforcement Learning (RL) with Guides to improve the closed-loop behavior by learning from the additional interactions with the valve. We test the proposed control method in various scenarios on three different valves, all highlighting the benefits of combining both PI and RL frameworks to improve control performance in non-linear stochastic systems. In all the experimental test cases, the resulting agent has a better sample efficiency than traditional RL agents and outperforms the PI controller.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Closed loops ; Control methods ; Controllers ; Nonlinear control ; Nonlinear systems ; Proportional integral ; Stochastic systems ; Valves</subject><ispartof>arXiv.org, 2024-07</ispartof><rights>2024. 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>780,784</link.rule.ids></links><search><creatorcontrib>Daoudi, Paul</creatorcontrib><creatorcontrib>Mavkov, Bojan</creatorcontrib><creatorcontrib>Robu, Bogdan</creatorcontrib><creatorcontrib>Prieur, Christophe</creatorcontrib><creatorcontrib>Witrant, Emmanuel</creatorcontrib><creatorcontrib>Barlier, Merwan</creatorcontrib><creatorcontrib>Ludovic Dos Santos</creatorcontrib><title>Improving a Proportional Integral Controller with Reinforcement Learning on a Throttle Valve Benchmark</title><title>arXiv.org</title><description>This paper presents a learning-based control strategy for non-linear throttle valves with an asymmetric hysteresis, leading to a near-optimal controller without requiring any prior knowledge about the environment. We start with a carefully tuned Proportional Integrator (PI) controller and exploit the recent advances in Reinforcement Learning (RL) with Guides to improve the closed-loop behavior by learning from the additional interactions with the valve. We test the proposed control method in various scenarios on three different valves, all highlighting the benefits of combining both PI and RL frameworks to improve control performance in non-linear stochastic systems. In all the experimental test cases, the resulting agent has a better sample efficiency than traditional RL agents and outperforms the PI controller.</description><subject>Closed loops</subject><subject>Control methods</subject><subject>Controllers</subject><subject>Nonlinear control</subject><subject>Nonlinear systems</subject><subject>Proportional integral</subject><subject>Stochastic systems</subject><subject>Valves</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNjcEKwjAQRIMgWLT_EPBciIm19qooCh5ExGsJZWur6a5uUv19K_gBnmYO8-YNRKSNmSXLudYjEXt_U0rpRabT1ESi2rcPpleDV2nlkelBHBpC6-QeA1y5L2vCwOQcsHw3oZYnaLAiLqEFDPIAlvGLE_YP55opBAfyYt0L5AqwrFvL94kYVtZ5iH85FtPt5rzeJb382YEPxY067rW-0LlRKstVmpn_Vh8RxkeY</recordid><startdate>20240715</startdate><enddate>20240715</enddate><creator>Daoudi, Paul</creator><creator>Mavkov, Bojan</creator><creator>Robu, Bogdan</creator><creator>Prieur, Christophe</creator><creator>Witrant, Emmanuel</creator><creator>Barlier, Merwan</creator><creator>Ludovic Dos Santos</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>20240715</creationdate><title>Improving a Proportional Integral Controller with Reinforcement Learning on a Throttle Valve Benchmark</title><author>Daoudi, Paul ; Mavkov, Bojan ; Robu, Bogdan ; Prieur, Christophe ; Witrant, Emmanuel ; Barlier, Merwan ; Ludovic Dos Santos</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_29300790573</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Closed loops</topic><topic>Control methods</topic><topic>Controllers</topic><topic>Nonlinear control</topic><topic>Nonlinear systems</topic><topic>Proportional integral</topic><topic>Stochastic systems</topic><topic>Valves</topic><toplevel>online_resources</toplevel><creatorcontrib>Daoudi, Paul</creatorcontrib><creatorcontrib>Mavkov, Bojan</creatorcontrib><creatorcontrib>Robu, Bogdan</creatorcontrib><creatorcontrib>Prieur, Christophe</creatorcontrib><creatorcontrib>Witrant, Emmanuel</creatorcontrib><creatorcontrib>Barlier, Merwan</creatorcontrib><creatorcontrib>Ludovic Dos Santos</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>Daoudi, Paul</au><au>Mavkov, Bojan</au><au>Robu, Bogdan</au><au>Prieur, Christophe</au><au>Witrant, Emmanuel</au><au>Barlier, Merwan</au><au>Ludovic Dos Santos</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Improving a Proportional Integral Controller with Reinforcement Learning on a Throttle Valve Benchmark</atitle><jtitle>arXiv.org</jtitle><date>2024-07-15</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>This paper presents a learning-based control strategy for non-linear throttle valves with an asymmetric hysteresis, leading to a near-optimal controller without requiring any prior knowledge about the environment. We start with a carefully tuned Proportional Integrator (PI) controller and exploit the recent advances in Reinforcement Learning (RL) with Guides to improve the closed-loop behavior by learning from the additional interactions with the valve. We test the proposed control method in various scenarios on three different valves, all highlighting the benefits of combining both PI and RL frameworks to improve control performance in non-linear stochastic systems. In all the experimental test cases, the resulting agent has a better sample efficiency than traditional RL agents and outperforms the PI controller.</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, 2024-07 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2930079057 |
source | Free E- Journals |
subjects | Closed loops Control methods Controllers Nonlinear control Nonlinear systems Proportional integral Stochastic systems Valves |
title | Improving a Proportional Integral Controller with Reinforcement Learning on a Throttle Valve Benchmark |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T13%3A22%3A24IST&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=Improving%20a%20Proportional%20Integral%20Controller%20with%20Reinforcement%20Learning%20on%20a%20Throttle%20Valve%20Benchmark&rft.jtitle=arXiv.org&rft.au=Daoudi,%20Paul&rft.date=2024-07-15&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2930079057%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2930079057&rft_id=info:pmid/&rfr_iscdi=true |