Adaptive critic control with multi‐step policy evaluation for nonlinear zero‐sum games
To attenuate the effect of disturbances on control performance, a multi‐step adaptive critic control (MsACC) framework is developed to solve zero‐sum games for discrete‐time nonlinear systems. The MsACC algorithm utilizes multi‐step policy evaluation to obtain the solution of the Hamilton–Jacobi–Isa...
Gespeichert in:
| Veröffentlicht in: | International journal of robust and nonlinear control 2024-01, Vol.34 (1), p.551-566 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 566 |
|---|---|
| container_issue | 1 |
| container_start_page | 551 |
| container_title | International journal of robust and nonlinear control |
| container_volume | 34 |
| creator | Li, Xin Wang, Ding Wang, Jiangyu Qiao, Junfei |
| description | To attenuate the effect of disturbances on control performance, a multi‐step adaptive critic control (MsACC) framework is developed to solve zero‐sum games for discrete‐time nonlinear systems. The MsACC algorithm utilizes multi‐step policy evaluation to obtain the solution of the Hamilton–Jacobi–Isaac equation, which is faster than that of the one‐step policy evaluation. The convergence rate of the MsACC algorithm is adjustable by varying the step size of the policy evaluation. In addition, the stability and convergence of the MsACC algorithm are proved under certain conditions. In order to realize the MsACC algorithm, three neural networks are established to approximate the control input, the disturbance input, and the cost function, respectively. Finally, the effectiveness of the MsACC algorithm is verified by two simulation examples, including a linear system and a nonlinear plant. |
| doi_str_mv | 10.1002/rnc.6984 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2900112449</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2900112449</sourcerecordid><originalsourceid>FETCH-LOGICAL-c255t-afda5ed73ad3183d58c4701ba3f9314a1f6d15c20cfaf64fbee233681a1ecb1a3</originalsourceid><addsrcrecordid>eNotkM1KAzEUhYMoWKvgIwTcuJmam2Smk2Up_kHBjW7cDLeZRFNmJmOSqdSVj-Az-iROqat74H6cAx8hl8BmwBi_CZ2eFaqUR2QCTKkMuFDH-yxVViouTslZjBvGxh-XE_K6qLFPbmuoDi45TbXvUvAN_XTpnbZDk9zv909Mpqe9b5zeUbPFZsDkfEetD7TzXeM6g4F-meD37NDSN2xNPCcnFptoLv7vlLzc3T4vH7LV0_3jcrHKNM_zlKGtMTf1XGAtoBR1Xmo5Z7BGYZUAiWCLGnLNmbZoC2nXxnAhihIQjF4Diim5OvT2wX8MJqZq44fQjZMVV4wBcCnVSF0fKB18jMHYqg-uxbCrgFV7c9VortqbE39JiWUI</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2900112449</pqid></control><display><type>article</type><title>Adaptive critic control with multi‐step policy evaluation for nonlinear zero‐sum games</title><source>Access via Wiley Online Library</source><creator>Li, Xin ; Wang, Ding ; Wang, Jiangyu ; Qiao, Junfei</creator><creatorcontrib>Li, Xin ; Wang, Ding ; Wang, Jiangyu ; Qiao, Junfei</creatorcontrib><description>To attenuate the effect of disturbances on control performance, a multi‐step adaptive critic control (MsACC) framework is developed to solve zero‐sum games for discrete‐time nonlinear systems. The MsACC algorithm utilizes multi‐step policy evaluation to obtain the solution of the Hamilton–Jacobi–Isaac equation, which is faster than that of the one‐step policy evaluation. The convergence rate of the MsACC algorithm is adjustable by varying the step size of the policy evaluation. In addition, the stability and convergence of the MsACC algorithm are proved under certain conditions. In order to realize the MsACC algorithm, three neural networks are established to approximate the control input, the disturbance input, and the cost function, respectively. Finally, the effectiveness of the MsACC algorithm is verified by two simulation examples, including a linear system and a nonlinear plant.</description><identifier>ISSN: 1049-8923</identifier><identifier>EISSN: 1099-1239</identifier><identifier>DOI: 10.1002/rnc.6984</identifier><language>eng</language><publisher>Bognor Regis: Wiley Subscription Services, Inc</publisher><subject>Adaptive control ; Algorithms ; Convergence ; Cost function ; Discrete time systems ; Games ; Neural networks ; Nonlinear systems ; Stability analysis ; Sums</subject><ispartof>International journal of robust and nonlinear control, 2024-01, Vol.34 (1), p.551-566</ispartof><rights>2024 John Wiley & Sons, Ltd.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c255t-afda5ed73ad3183d58c4701ba3f9314a1f6d15c20cfaf64fbee233681a1ecb1a3</citedby><cites>FETCH-LOGICAL-c255t-afda5ed73ad3183d58c4701ba3f9314a1f6d15c20cfaf64fbee233681a1ecb1a3</cites><orcidid>0000-0002-7149-5712 ; 0000-0001-9652-3364</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Li, Xin</creatorcontrib><creatorcontrib>Wang, Ding</creatorcontrib><creatorcontrib>Wang, Jiangyu</creatorcontrib><creatorcontrib>Qiao, Junfei</creatorcontrib><title>Adaptive critic control with multi‐step policy evaluation for nonlinear zero‐sum games</title><title>International journal of robust and nonlinear control</title><description>To attenuate the effect of disturbances on control performance, a multi‐step adaptive critic control (MsACC) framework is developed to solve zero‐sum games for discrete‐time nonlinear systems. The MsACC algorithm utilizes multi‐step policy evaluation to obtain the solution of the Hamilton–Jacobi–Isaac equation, which is faster than that of the one‐step policy evaluation. The convergence rate of the MsACC algorithm is adjustable by varying the step size of the policy evaluation. In addition, the stability and convergence of the MsACC algorithm are proved under certain conditions. In order to realize the MsACC algorithm, three neural networks are established to approximate the control input, the disturbance input, and the cost function, respectively. Finally, the effectiveness of the MsACC algorithm is verified by two simulation examples, including a linear system and a nonlinear plant.</description><subject>Adaptive control</subject><subject>Algorithms</subject><subject>Convergence</subject><subject>Cost function</subject><subject>Discrete time systems</subject><subject>Games</subject><subject>Neural networks</subject><subject>Nonlinear systems</subject><subject>Stability analysis</subject><subject>Sums</subject><issn>1049-8923</issn><issn>1099-1239</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNotkM1KAzEUhYMoWKvgIwTcuJmam2Smk2Up_kHBjW7cDLeZRFNmJmOSqdSVj-Az-iROqat74H6cAx8hl8BmwBi_CZ2eFaqUR2QCTKkMuFDH-yxVViouTslZjBvGxh-XE_K6qLFPbmuoDi45TbXvUvAN_XTpnbZDk9zv909Mpqe9b5zeUbPFZsDkfEetD7TzXeM6g4F-meD37NDSN2xNPCcnFptoLv7vlLzc3T4vH7LV0_3jcrHKNM_zlKGtMTf1XGAtoBR1Xmo5Z7BGYZUAiWCLGnLNmbZoC2nXxnAhihIQjF4Diim5OvT2wX8MJqZq44fQjZMVV4wBcCnVSF0fKB18jMHYqg-uxbCrgFV7c9VortqbE39JiWUI</recordid><startdate>20240110</startdate><enddate>20240110</enddate><creator>Li, Xin</creator><creator>Wang, Ding</creator><creator>Wang, Jiangyu</creator><creator>Qiao, Junfei</creator><general>Wiley Subscription Services, Inc</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-7149-5712</orcidid><orcidid>https://orcid.org/0000-0001-9652-3364</orcidid></search><sort><creationdate>20240110</creationdate><title>Adaptive critic control with multi‐step policy evaluation for nonlinear zero‐sum games</title><author>Li, Xin ; Wang, Ding ; Wang, Jiangyu ; Qiao, Junfei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c255t-afda5ed73ad3183d58c4701ba3f9314a1f6d15c20cfaf64fbee233681a1ecb1a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Adaptive control</topic><topic>Algorithms</topic><topic>Convergence</topic><topic>Cost function</topic><topic>Discrete time systems</topic><topic>Games</topic><topic>Neural networks</topic><topic>Nonlinear systems</topic><topic>Stability analysis</topic><topic>Sums</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Li, Xin</creatorcontrib><creatorcontrib>Wang, Ding</creatorcontrib><creatorcontrib>Wang, Jiangyu</creatorcontrib><creatorcontrib>Qiao, Junfei</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>International journal of robust and nonlinear control</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Li, Xin</au><au>Wang, Ding</au><au>Wang, Jiangyu</au><au>Qiao, Junfei</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Adaptive critic control with multi‐step policy evaluation for nonlinear zero‐sum games</atitle><jtitle>International journal of robust and nonlinear control</jtitle><date>2024-01-10</date><risdate>2024</risdate><volume>34</volume><issue>1</issue><spage>551</spage><epage>566</epage><pages>551-566</pages><issn>1049-8923</issn><eissn>1099-1239</eissn><abstract>To attenuate the effect of disturbances on control performance, a multi‐step adaptive critic control (MsACC) framework is developed to solve zero‐sum games for discrete‐time nonlinear systems. The MsACC algorithm utilizes multi‐step policy evaluation to obtain the solution of the Hamilton–Jacobi–Isaac equation, which is faster than that of the one‐step policy evaluation. The convergence rate of the MsACC algorithm is adjustable by varying the step size of the policy evaluation. In addition, the stability and convergence of the MsACC algorithm are proved under certain conditions. In order to realize the MsACC algorithm, three neural networks are established to approximate the control input, the disturbance input, and the cost function, respectively. Finally, the effectiveness of the MsACC algorithm is verified by two simulation examples, including a linear system and a nonlinear plant.</abstract><cop>Bognor Regis</cop><pub>Wiley Subscription Services, Inc</pub><doi>10.1002/rnc.6984</doi><tpages>16</tpages><orcidid>https://orcid.org/0000-0002-7149-5712</orcidid><orcidid>https://orcid.org/0000-0001-9652-3364</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1049-8923 |
| ispartof | International journal of robust and nonlinear control, 2024-01, Vol.34 (1), p.551-566 |
| issn | 1049-8923 1099-1239 |
| language | eng |
| recordid | cdi_proquest_journals_2900112449 |
| source | Access via Wiley Online Library |
| subjects | Adaptive control Algorithms Convergence Cost function Discrete time systems Games Neural networks Nonlinear systems Stability analysis Sums |
| title | Adaptive critic control with multi‐step policy evaluation for nonlinear zero‐sum games |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T08%3A20%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Adaptive%20critic%20control%20with%20multi%E2%80%90step%20policy%20evaluation%20for%20nonlinear%20zero%E2%80%90sum%20games&rft.jtitle=International%20journal%20of%20robust%20and%20nonlinear%20control&rft.au=Li,%20Xin&rft.date=2024-01-10&rft.volume=34&rft.issue=1&rft.spage=551&rft.epage=566&rft.pages=551-566&rft.issn=1049-8923&rft.eissn=1099-1239&rft_id=info:doi/10.1002/rnc.6984&rft_dat=%3Cproquest_cross%3E2900112449%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2900112449&rft_id=info:pmid/&rfr_iscdi=true |