Reinforcement Learning Based on Active Learning Method
In this paper, a new reinforcement learning approach is proposed which is based on a powerful concept named Active Learning Method (ALM) in modeling. ALM expresses any multi-input-single-output system as a fuzzy combination of some single-input-single output systems. The proposed method is an actor-...
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 | 602 |
|---|---|
| container_issue | |
| container_start_page | 598 |
| container_title | |
| container_volume | 2 |
| creator | Sagha, H. Shouraki, S.B. Khasteh, H. Kiaei, A.A. |
| description | In this paper, a new reinforcement learning approach is proposed which is based on a powerful concept named Active Learning Method (ALM) in modeling. ALM expresses any multi-input-single-output system as a fuzzy combination of some single-input-single output systems. The proposed method is an actor-critic system similar to Generalized Approximate Reasoning based Intelligent Control (GARIC) structure to adapt the ALM by delayed reinforcement signals. Our system uses Temporal Difference (TD) learning to model the behavior of useful actions of a control system. The goodness of an action is modeled on Reward-Penalty-Plane. IDS planes will be updated according to this plane. It is shown that the system can learn with a predefined fuzzy system or without it (through random actions). |
| doi_str_mv | 10.1109/IITA.2008.565 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4739834</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4739834</ieee_id><sourcerecordid>4739834</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-7715d3265c9378662f079777124f1647eedac43d65328954cb8b3706526d198a3</originalsourceid><addsrcrecordid>eNpFjU1LxEAQRAdkQV1z9OQlfyCx56OnZ45xUTcQEWQ9L7OZjo64iSRB8N8bUfBUj3pQJcSlhFJK8Nd1vatKBeBKtHgiMk8OyHrUZqGVOP9RHhxKPBXZNL0BgPSWJOKZsE-c-m4YWz5yP-cNh7FP_Ut-EyaO-dDnVTunT_4XDzy_DvFCrLrwPnH2l2vxfHe722yL5vG-3lRNkSThXNByErWy2HpNzlrVAXlaWmU6aQ0xx9AaHS1q5Tya9uAOmsCislF6F_RaXP3uJmbef4zpGMavvSHtnTb6G_UXQ-0</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Reinforcement Learning Based on Active Learning Method</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Sagha, H. ; Shouraki, S.B. ; Khasteh, H. ; Kiaei, A.A.</creator><creatorcontrib>Sagha, H. ; Shouraki, S.B. ; Khasteh, H. ; Kiaei, A.A.</creatorcontrib><description>In this paper, a new reinforcement learning approach is proposed which is based on a powerful concept named Active Learning Method (ALM) in modeling. ALM expresses any multi-input-single-output system as a fuzzy combination of some single-input-single output systems. The proposed method is an actor-critic system similar to Generalized Approximate Reasoning based Intelligent Control (GARIC) structure to adapt the ALM by delayed reinforcement signals. Our system uses Temporal Difference (TD) learning to model the behavior of useful actions of a control system. The goodness of an action is modeled on Reward-Penalty-Plane. IDS planes will be updated according to this plane. It is shown that the system can learn with a predefined fuzzy system or without it (through random actions).</description><identifier>ISBN: 9780769534978</identifier><identifier>ISBN: 076953497X</identifier><identifier>DOI: 10.1109/IITA.2008.565</identifier><identifier>LCCN: 2008908515</identifier><language>eng</language><publisher>IEEE</publisher><subject>Active Learning Method ; Control system synthesis ; Data mining ; Delay ; Fuzzy Control ; Fuzzy systems ; Gravity ; Information technology ; Intelligent control ; Intrusion detection ; Learning systems ; Power system modeling ; Reinforcement Learning</subject><ispartof>2008 Second International Symposium on Intelligent Information Technology Application, 2008, Vol.2, p.598-602</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4739834$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2057,27924,54919</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4739834$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Sagha, H.</creatorcontrib><creatorcontrib>Shouraki, S.B.</creatorcontrib><creatorcontrib>Khasteh, H.</creatorcontrib><creatorcontrib>Kiaei, A.A.</creatorcontrib><title>Reinforcement Learning Based on Active Learning Method</title><title>2008 Second International Symposium on Intelligent Information Technology Application</title><addtitle>IITA</addtitle><description>In this paper, a new reinforcement learning approach is proposed which is based on a powerful concept named Active Learning Method (ALM) in modeling. ALM expresses any multi-input-single-output system as a fuzzy combination of some single-input-single output systems. The proposed method is an actor-critic system similar to Generalized Approximate Reasoning based Intelligent Control (GARIC) structure to adapt the ALM by delayed reinforcement signals. Our system uses Temporal Difference (TD) learning to model the behavior of useful actions of a control system. The goodness of an action is modeled on Reward-Penalty-Plane. IDS planes will be updated according to this plane. It is shown that the system can learn with a predefined fuzzy system or without it (through random actions).</description><subject>Active Learning Method</subject><subject>Control system synthesis</subject><subject>Data mining</subject><subject>Delay</subject><subject>Fuzzy Control</subject><subject>Fuzzy systems</subject><subject>Gravity</subject><subject>Information technology</subject><subject>Intelligent control</subject><subject>Intrusion detection</subject><subject>Learning systems</subject><subject>Power system modeling</subject><subject>Reinforcement Learning</subject><isbn>9780769534978</isbn><isbn>076953497X</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2008</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpFjU1LxEAQRAdkQV1z9OQlfyCx56OnZ45xUTcQEWQ9L7OZjo64iSRB8N8bUfBUj3pQJcSlhFJK8Nd1vatKBeBKtHgiMk8OyHrUZqGVOP9RHhxKPBXZNL0BgPSWJOKZsE-c-m4YWz5yP-cNh7FP_Ut-EyaO-dDnVTunT_4XDzy_DvFCrLrwPnH2l2vxfHe722yL5vG-3lRNkSThXNByErWy2HpNzlrVAXlaWmU6aQ0xx9AaHS1q5Tya9uAOmsCislF6F_RaXP3uJmbef4zpGMavvSHtnTb6G_UXQ-0</recordid><startdate>200812</startdate><enddate>200812</enddate><creator>Sagha, H.</creator><creator>Shouraki, S.B.</creator><creator>Khasteh, H.</creator><creator>Kiaei, A.A.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200812</creationdate><title>Reinforcement Learning Based on Active Learning Method</title><author>Sagha, H. ; Shouraki, S.B. ; Khasteh, H. ; Kiaei, A.A.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-7715d3265c9378662f079777124f1647eedac43d65328954cb8b3706526d198a3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Active Learning Method</topic><topic>Control system synthesis</topic><topic>Data mining</topic><topic>Delay</topic><topic>Fuzzy Control</topic><topic>Fuzzy systems</topic><topic>Gravity</topic><topic>Information technology</topic><topic>Intelligent control</topic><topic>Intrusion detection</topic><topic>Learning systems</topic><topic>Power system modeling</topic><topic>Reinforcement Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Sagha, H.</creatorcontrib><creatorcontrib>Shouraki, S.B.</creatorcontrib><creatorcontrib>Khasteh, H.</creatorcontrib><creatorcontrib>Kiaei, A.A.</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>Sagha, H.</au><au>Shouraki, S.B.</au><au>Khasteh, H.</au><au>Kiaei, A.A.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Reinforcement Learning Based on Active Learning Method</atitle><btitle>2008 Second International Symposium on Intelligent Information Technology Application</btitle><stitle>IITA</stitle><date>2008-12</date><risdate>2008</risdate><volume>2</volume><spage>598</spage><epage>602</epage><pages>598-602</pages><isbn>9780769534978</isbn><isbn>076953497X</isbn><abstract>In this paper, a new reinforcement learning approach is proposed which is based on a powerful concept named Active Learning Method (ALM) in modeling. ALM expresses any multi-input-single-output system as a fuzzy combination of some single-input-single output systems. The proposed method is an actor-critic system similar to Generalized Approximate Reasoning based Intelligent Control (GARIC) structure to adapt the ALM by delayed reinforcement signals. Our system uses Temporal Difference (TD) learning to model the behavior of useful actions of a control system. The goodness of an action is modeled on Reward-Penalty-Plane. IDS planes will be updated according to this plane. It is shown that the system can learn with a predefined fuzzy system or without it (through random actions).</abstract><pub>IEEE</pub><doi>10.1109/IITA.2008.565</doi><tpages>5</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 9780769534978 |
| ispartof | 2008 Second International Symposium on Intelligent Information Technology Application, 2008, Vol.2, p.598-602 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_4739834 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Active Learning Method Control system synthesis Data mining Delay Fuzzy Control Fuzzy systems Gravity Information technology Intelligent control Intrusion detection Learning systems Power system modeling Reinforcement Learning |
| title | Reinforcement Learning Based on Active Learning Method |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T07%3A55%3A17IST&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=Reinforcement%20Learning%20Based%20on%20Active%20Learning%20Method&rft.btitle=2008%20Second%20International%20Symposium%20on%20Intelligent%20Information%20Technology%20Application&rft.au=Sagha,%20H.&rft.date=2008-12&rft.volume=2&rft.spage=598&rft.epage=602&rft.pages=598-602&rft.isbn=9780769534978&rft.isbn_list=076953497X&rft_id=info:doi/10.1109/IITA.2008.565&rft_dat=%3Cieee_6IE%3E4739834%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4739834&rfr_iscdi=true |