Simulation of the evolution of autonomous adaptive agents
A model of evolving populations of self-learning agents is studied, and the interaction between learning and evolution is analyzed. Each agent is equipped with a neural network (NN) adaptive critic design for behavioral adaptation. The model is investigated by an example of a simple agent-broker tha...
Gespeichert in:
| Veröffentlicht in: | Mathematical models and computer simulations 2009-02, Vol.1 (1), p.156-164 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 164 |
|---|---|
| container_issue | 1 |
| container_start_page | 156 |
| container_title | Mathematical models and computer simulations |
| container_volume | 1 |
| creator | Mosalov, O. P. Red’ko, V. G. Prokhorov, D. V. |
| description | A model of evolving populations of self-learning agents is studied, and the interaction between learning and evolution is analyzed. Each agent is equipped with a neural network (NN) adaptive critic design for behavioral adaptation. The model is investigated by an example of a simple agent-broker that predicts stock price changes and uses these predictions for choosing strategies. Three variants of the model are compared, which include either learning and evolution, or only evolution, or only learning. It is shown that the model may exhibit the Baldwin effect; i.e., initially acquired adaptive policy of agents becomes inheritable during evolution. The behavior of the model agents is compared with the searching behavior of simple animals. |
| doi_str_mv | 10.1134/S2070048209010177 |
| format | Article |
| fullrecord | <record><control><sourceid>crossref_sprin</sourceid><recordid>TN_cdi_crossref_primary_10_1134_S2070048209010177</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_1134_S2070048209010177</sourcerecordid><originalsourceid>FETCH-LOGICAL-c1557-d7275f8d1602fae4f1701ce4910e5845a82d84f61a86d641051997d49bcb071c3</originalsourceid><addsrcrecordid>eNp9j81qwzAQhEVpoSHNA_TmF3C7K0uWdCyhfxDoIe1ZKPpJHWwrSHagb1-HtLkUupdZhv2GHUJuEe4QK3a_piAAmKSgAAGFuCCzo1UCU3B53iW9JoucdzBNRYWs5IyoddONrRma2BcxFMOnL_whtuOvYcYh9rGLYy6MM_uhOfjCbH0_5BtyFUyb_eJH5-Tj6fF9-VKu3p5flw-r0iLnonSCCh6kwxpoMJ4FFIDWM4XguWTcSOokCzUaWbuaIXBUSjimNnYDAm01J3jKtSnmnHzQ-9R0Jn1pBH2sr__Unxh6YvJ022990rs4pn568x_oG8hcWsM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Simulation of the evolution of autonomous adaptive agents</title><source>Springer Nature - Complete Springer Journals</source><creator>Mosalov, O. P. ; Red’ko, V. G. ; Prokhorov, D. V.</creator><creatorcontrib>Mosalov, O. P. ; Red’ko, V. G. ; Prokhorov, D. V.</creatorcontrib><description>A model of evolving populations of self-learning agents is studied, and the interaction between learning and evolution is analyzed. Each agent is equipped with a neural network (NN) adaptive critic design for behavioral adaptation. The model is investigated by an example of a simple agent-broker that predicts stock price changes and uses these predictions for choosing strategies. Three variants of the model are compared, which include either learning and evolution, or only evolution, or only learning. It is shown that the model may exhibit the Baldwin effect; i.e., initially acquired adaptive policy of agents becomes inheritable during evolution. The behavior of the model agents is compared with the searching behavior of simple animals.</description><identifier>ISSN: 2070-0482</identifier><identifier>EISSN: 2070-0490</identifier><identifier>DOI: 10.1134/S2070048209010177</identifier><language>eng</language><publisher>Dordrecht: SP MAIK Nauka/Interperiodica</publisher><subject>Mathematical Modeling and Industrial Mathematics ; Mathematics ; Mathematics and Statistics ; Simulation and Modeling</subject><ispartof>Mathematical models and computer simulations, 2009-02, Vol.1 (1), p.156-164</ispartof><rights>Pleiades Publishing, Ltd. 2009</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c1557-d7275f8d1602fae4f1701ce4910e5845a82d84f61a86d641051997d49bcb071c3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1134/S2070048209010177$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1134/S2070048209010177$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,776,780,27901,27902,41464,42533,51294</link.rule.ids></links><search><creatorcontrib>Mosalov, O. P.</creatorcontrib><creatorcontrib>Red’ko, V. G.</creatorcontrib><creatorcontrib>Prokhorov, D. V.</creatorcontrib><title>Simulation of the evolution of autonomous adaptive agents</title><title>Mathematical models and computer simulations</title><addtitle>Math Models Comput Simul</addtitle><description>A model of evolving populations of self-learning agents is studied, and the interaction between learning and evolution is analyzed. Each agent is equipped with a neural network (NN) adaptive critic design for behavioral adaptation. The model is investigated by an example of a simple agent-broker that predicts stock price changes and uses these predictions for choosing strategies. Three variants of the model are compared, which include either learning and evolution, or only evolution, or only learning. It is shown that the model may exhibit the Baldwin effect; i.e., initially acquired adaptive policy of agents becomes inheritable during evolution. The behavior of the model agents is compared with the searching behavior of simple animals.</description><subject>Mathematical Modeling and Industrial Mathematics</subject><subject>Mathematics</subject><subject>Mathematics and Statistics</subject><subject>Simulation and Modeling</subject><issn>2070-0482</issn><issn>2070-0490</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2009</creationdate><recordtype>article</recordtype><recordid>eNp9j81qwzAQhEVpoSHNA_TmF3C7K0uWdCyhfxDoIe1ZKPpJHWwrSHagb1-HtLkUupdZhv2GHUJuEe4QK3a_piAAmKSgAAGFuCCzo1UCU3B53iW9JoucdzBNRYWs5IyoddONrRma2BcxFMOnL_whtuOvYcYh9rGLYy6MM_uhOfjCbH0_5BtyFUyb_eJH5-Tj6fF9-VKu3p5flw-r0iLnonSCCh6kwxpoMJ4FFIDWM4XguWTcSOokCzUaWbuaIXBUSjimNnYDAm01J3jKtSnmnHzQ-9R0Jn1pBH2sr__Unxh6YvJ022990rs4pn568x_oG8hcWsM</recordid><startdate>20090201</startdate><enddate>20090201</enddate><creator>Mosalov, O. P.</creator><creator>Red’ko, V. G.</creator><creator>Prokhorov, D. V.</creator><general>SP MAIK Nauka/Interperiodica</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20090201</creationdate><title>Simulation of the evolution of autonomous adaptive agents</title><author>Mosalov, O. P. ; Red’ko, V. G. ; Prokhorov, D. V.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c1557-d7275f8d1602fae4f1701ce4910e5845a82d84f61a86d641051997d49bcb071c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2009</creationdate><topic>Mathematical Modeling and Industrial Mathematics</topic><topic>Mathematics</topic><topic>Mathematics and Statistics</topic><topic>Simulation and Modeling</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Mosalov, O. P.</creatorcontrib><creatorcontrib>Red’ko, V. G.</creatorcontrib><creatorcontrib>Prokhorov, D. V.</creatorcontrib><collection>CrossRef</collection><jtitle>Mathematical models and computer simulations</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Mosalov, O. P.</au><au>Red’ko, V. G.</au><au>Prokhorov, D. V.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Simulation of the evolution of autonomous adaptive agents</atitle><jtitle>Mathematical models and computer simulations</jtitle><stitle>Math Models Comput Simul</stitle><date>2009-02-01</date><risdate>2009</risdate><volume>1</volume><issue>1</issue><spage>156</spage><epage>164</epage><pages>156-164</pages><issn>2070-0482</issn><eissn>2070-0490</eissn><abstract>A model of evolving populations of self-learning agents is studied, and the interaction between learning and evolution is analyzed. Each agent is equipped with a neural network (NN) adaptive critic design for behavioral adaptation. The model is investigated by an example of a simple agent-broker that predicts stock price changes and uses these predictions for choosing strategies. Three variants of the model are compared, which include either learning and evolution, or only evolution, or only learning. It is shown that the model may exhibit the Baldwin effect; i.e., initially acquired adaptive policy of agents becomes inheritable during evolution. The behavior of the model agents is compared with the searching behavior of simple animals.</abstract><cop>Dordrecht</cop><pub>SP MAIK Nauka/Interperiodica</pub><doi>10.1134/S2070048209010177</doi><tpages>9</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2070-0482 |
| ispartof | Mathematical models and computer simulations, 2009-02, Vol.1 (1), p.156-164 |
| issn | 2070-0482 2070-0490 |
| language | eng |
| recordid | cdi_crossref_primary_10_1134_S2070048209010177 |
| source | Springer Nature - Complete Springer Journals |
| subjects | Mathematical Modeling and Industrial Mathematics Mathematics Mathematics and Statistics Simulation and Modeling |
| title | Simulation of the evolution of autonomous adaptive agents |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-29T21%3A06%3A29IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref_sprin&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Simulation%20of%20the%20evolution%20of%20autonomous%20adaptive%20agents&rft.jtitle=Mathematical%20models%20and%20computer%20simulations&rft.au=Mosalov,%20O.%20P.&rft.date=2009-02-01&rft.volume=1&rft.issue=1&rft.spage=156&rft.epage=164&rft.pages=156-164&rft.issn=2070-0482&rft.eissn=2070-0490&rft_id=info:doi/10.1134/S2070048209010177&rft_dat=%3Ccrossref_sprin%3E10_1134_S2070048209010177%3C/crossref_sprin%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |