A penalty function method for exploratory adaptive-critic neural network control
A constrained penalty function method for exploratory adaptive-critic neural network (NN) control is presented. While constrained approximate dynamic programming has been effective to guarantee closed-loop system performance and stability objectives, in the presence of a change in the plant dynamics...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1414 |
|---|---|
| container_issue | |
| container_start_page | 1410 |
| container_title | |
| container_volume | |
| creator | Di Muro, G. Ferrari, S. |
| description | A constrained penalty function method for exploratory adaptive-critic neural network (NN) control is presented. While constrained approximate dynamic programming has been effective to guarantee closed-loop system performance and stability objectives, in the presence of a change in the plant dynamics it may not have the necessary plasticity to explore and fully adapt to the new behaviors of the plant, if these violate the constraints. A generalized constrained approach is introduced to overcome these limitations. Through this methodology it is shown that NNs are not only capable to acquire new plasticity when necessary, but also can adjust their parametric structure reducing their hidden nodes and becoming more computationally efficient. |
| doi_str_mv | 10.1109/MED.2009.5164744 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5164744</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5164744</ieee_id><sourcerecordid>5164744</sourcerecordid><originalsourceid>FETCH-LOGICAL-i105t-7cc949da9ecadf3befbfab359a9151bd57af43be4030cc14ba323f66113831543</originalsourceid><addsrcrecordid>eNo1kD1PwzAYhI1QJWjJjsTiP5Bgx6_jeKxK-ZCKYIC5euPYwpDGkesC-fcEUW55dKfTDUfIJWcF50xfP65vipIxXUhegQI4IZlWNYcSAKpa1qdk_m-gnpH5b1czULU6I9l-_84mgRSMlefkeUkH22OXRuoOvUk-9HRn01toqQuR2u-hCxFTiCPFFofkP21uok_e0N4eInYT0leIH9SEPsXQXZCZw25vsyMX5PV2_bK6zzdPdw-r5Sb3nMmUK2M06Ba1Ndg60VjXOGyE1Ki55E0rFTqYYmCCGcOhQVEKV1Wci1pwCWJBrv52vbV2O0S_wzhuj4-IH3VAU6o</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A penalty function method for exploratory adaptive-critic neural network control</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Di Muro, G. ; Ferrari, S.</creator><creatorcontrib>Di Muro, G. ; Ferrari, S.</creatorcontrib><description>A constrained penalty function method for exploratory adaptive-critic neural network (NN) control is presented. While constrained approximate dynamic programming has been effective to guarantee closed-loop system performance and stability objectives, in the presence of a change in the plant dynamics it may not have the necessary plasticity to explore and fully adapt to the new behaviors of the plant, if these violate the constraints. A generalized constrained approach is introduced to overcome these limitations. Through this methodology it is shown that NNs are not only capable to acquire new plasticity when necessary, but also can adjust their parametric structure reducing their hidden nodes and becoming more computationally efficient.</description><identifier>ISBN: 1424446848</identifier><identifier>ISBN: 9781424446841</identifier><identifier>EISBN: 9781424446858</identifier><identifier>EISBN: 1424446856</identifier><identifier>DOI: 10.1109/MED.2009.5164744</identifier><identifier>LCCN: 2009904787</identifier><language>eng</language><publisher>IEEE</publisher><subject>Aerodynamics ; Approximate dynamic programming (ADP) ; Automatic control ; Automation ; constrained optimization ; Constraint optimization ; Cost function ; Dynamic programming ; forgetting ; Mechanical engineering ; Neural networks ; neural networks (NNs) ; Optimal control ; penalty function ; Stability</subject><ispartof>2009 17th Mediterranean Conference on Control and Automation, 2009, p.1410-1414</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5164744$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5164744$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Di Muro, G.</creatorcontrib><creatorcontrib>Ferrari, S.</creatorcontrib><title>A penalty function method for exploratory adaptive-critic neural network control</title><title>2009 17th Mediterranean Conference on Control and Automation</title><addtitle>MED</addtitle><description>A constrained penalty function method for exploratory adaptive-critic neural network (NN) control is presented. While constrained approximate dynamic programming has been effective to guarantee closed-loop system performance and stability objectives, in the presence of a change in the plant dynamics it may not have the necessary plasticity to explore and fully adapt to the new behaviors of the plant, if these violate the constraints. A generalized constrained approach is introduced to overcome these limitations. Through this methodology it is shown that NNs are not only capable to acquire new plasticity when necessary, but also can adjust their parametric structure reducing their hidden nodes and becoming more computationally efficient.</description><subject>Aerodynamics</subject><subject>Approximate dynamic programming (ADP)</subject><subject>Automatic control</subject><subject>Automation</subject><subject>constrained optimization</subject><subject>Constraint optimization</subject><subject>Cost function</subject><subject>Dynamic programming</subject><subject>forgetting</subject><subject>Mechanical engineering</subject><subject>Neural networks</subject><subject>neural networks (NNs)</subject><subject>Optimal control</subject><subject>penalty function</subject><subject>Stability</subject><isbn>1424446848</isbn><isbn>9781424446841</isbn><isbn>9781424446858</isbn><isbn>1424446856</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2009</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1kD1PwzAYhI1QJWjJjsTiP5Bgx6_jeKxK-ZCKYIC5euPYwpDGkesC-fcEUW55dKfTDUfIJWcF50xfP65vipIxXUhegQI4IZlWNYcSAKpa1qdk_m-gnpH5b1czULU6I9l-_84mgRSMlefkeUkH22OXRuoOvUk-9HRn01toqQuR2u-hCxFTiCPFFofkP21uok_e0N4eInYT0leIH9SEPsXQXZCZw25vsyMX5PV2_bK6zzdPdw-r5Sb3nMmUK2M06Ba1Ndg60VjXOGyE1Ki55E0rFTqYYmCCGcOhQVEKV1Wci1pwCWJBrv52vbV2O0S_wzhuj4-IH3VAU6o</recordid><startdate>200906</startdate><enddate>200906</enddate><creator>Di Muro, G.</creator><creator>Ferrari, S.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200906</creationdate><title>A penalty function method for exploratory adaptive-critic neural network control</title><author>Di Muro, G. ; Ferrari, S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i105t-7cc949da9ecadf3befbfab359a9151bd57af43be4030cc14ba323f66113831543</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2009</creationdate><topic>Aerodynamics</topic><topic>Approximate dynamic programming (ADP)</topic><topic>Automatic control</topic><topic>Automation</topic><topic>constrained optimization</topic><topic>Constraint optimization</topic><topic>Cost function</topic><topic>Dynamic programming</topic><topic>forgetting</topic><topic>Mechanical engineering</topic><topic>Neural networks</topic><topic>neural networks (NNs)</topic><topic>Optimal control</topic><topic>penalty function</topic><topic>Stability</topic><toplevel>online_resources</toplevel><creatorcontrib>Di Muro, G.</creatorcontrib><creatorcontrib>Ferrari, S.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Di Muro, G.</au><au>Ferrari, S.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A penalty function method for exploratory adaptive-critic neural network control</atitle><btitle>2009 17th Mediterranean Conference on Control and Automation</btitle><stitle>MED</stitle><date>2009-06</date><risdate>2009</risdate><spage>1410</spage><epage>1414</epage><pages>1410-1414</pages><isbn>1424446848</isbn><isbn>9781424446841</isbn><eisbn>9781424446858</eisbn><eisbn>1424446856</eisbn><abstract>A constrained penalty function method for exploratory adaptive-critic neural network (NN) control is presented. While constrained approximate dynamic programming has been effective to guarantee closed-loop system performance and stability objectives, in the presence of a change in the plant dynamics it may not have the necessary plasticity to explore and fully adapt to the new behaviors of the plant, if these violate the constraints. A generalized constrained approach is introduced to overcome these limitations. Through this methodology it is shown that NNs are not only capable to acquire new plasticity when necessary, but also can adjust their parametric structure reducing their hidden nodes and becoming more computationally efficient.</abstract><pub>IEEE</pub><doi>10.1109/MED.2009.5164744</doi><tpages>5</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 1424446848 |
| ispartof | 2009 17th Mediterranean Conference on Control and Automation, 2009, p.1410-1414 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_5164744 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Aerodynamics Approximate dynamic programming (ADP) Automatic control Automation constrained optimization Constraint optimization Cost function Dynamic programming forgetting Mechanical engineering Neural networks neural networks (NNs) Optimal control penalty function Stability |
| title | A penalty function method for exploratory adaptive-critic neural network control |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-19T14%3A16%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=A%20penalty%20function%20method%20for%20exploratory%20adaptive-critic%20neural%20network%20control&rft.btitle=2009%2017th%20Mediterranean%20Conference%20on%20Control%20and%20Automation&rft.au=Di%20Muro,%20G.&rft.date=2009-06&rft.spage=1410&rft.epage=1414&rft.pages=1410-1414&rft.isbn=1424446848&rft.isbn_list=9781424446841&rft_id=info:doi/10.1109/MED.2009.5164744&rft_dat=%3Cieee_6IE%3E5164744%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781424446858&rft.eisbn_list=1424446856&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5164744&rfr_iscdi=true |