Towards imitation-enhanced Reinforcement Learning in multi-agent systems
Imitation, in which an individual observes and copies another's actions, is a powerful means of learning. This paper presents a way of using imitation to enhance the learning capability of individual agents. The agents employ Q-learning and we show that agents with imitation enhanced Q-learning...
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 | 13 |
|---|---|
| container_issue | |
| container_start_page | 6 |
| container_title | |
| container_volume | |
| creator | Erbas, M. D. Winfield, A. F. T. Bull, L. |
| description | Imitation, in which an individual observes and copies another's actions, is a powerful means of learning. This paper presents a way of using imitation to enhance the learning capability of individual agents. The agents employ Q-learning and we show that agents with imitation enhanced Q-learning learn faster than those with Q-learning alone. |
| doi_str_mv | 10.1109/ALIFE.2011.5954652 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5954652</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5954652</ieee_id><sourcerecordid>5954652</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-13113d6c533921bb354df3055b37f5eeea185611495f2f58a5a307639d8689bc3</originalsourceid><addsrcrecordid>eNo9UF9LwzAcjP_AOfsF9KVfoDO__JI0eRxjc4OCIH0faZvMyJpKE5F9eytO7-Xg7ji4I-QB6AKA6qdltdusF4wCLIQWXAp2QTJdKpDAFKcS4JLMGEhaSFTsitz9GYxe_xslvyVZjO90gpSqlHxGtvXwZcYu5r73ySQ_hMKGNxNa2-Wv1gc3jK3tbUh5Zc0YfDjkPuT95zH5whx-9HiKyfbxntw4c4w2O_Oc1Jt1vdoW1cvzbrWsCq9pKgABsJOtQNQMmgYF7xxSIRosnbDWGlBiWsO1cMwJZYRBWkrUnZJKNy3OyeNvrZ_C-4_R92Y87c-f4DcDA1C-</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Towards imitation-enhanced Reinforcement Learning in multi-agent systems</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Erbas, M. D. ; Winfield, A. F. T. ; Bull, L.</creator><creatorcontrib>Erbas, M. D. ; Winfield, A. F. T. ; Bull, L.</creatorcontrib><description>Imitation, in which an individual observes and copies another's actions, is a powerful means of learning. This paper presents a way of using imitation to enhance the learning capability of individual agents. The agents employ Q-learning and we show that agents with imitation enhanced Q-learning learn faster than those with Q-learning alone.</description><identifier>ISSN: 2160-6374</identifier><identifier>ISBN: 1612840620</identifier><identifier>ISBN: 9781612840628</identifier><identifier>EISSN: 2160-6382</identifier><identifier>EISBN: 9781612840611</identifier><identifier>EISBN: 1612840612</identifier><identifier>EISBN: 9781612840635</identifier><identifier>EISBN: 1612840639</identifier><identifier>DOI: 10.1109/ALIFE.2011.5954652</identifier><language>eng</language><publisher>IEEE</publisher><subject>Actuators ; Adaptation models ; Electronic mail ; Greedy algorithms ; Learning ; Robots ; Watches</subject><ispartof>2011 IEEE Symposium on Artificial Life (ALIFE), 2011, p.6-13</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/5954652$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2056,27923,54918</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5954652$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Erbas, M. D.</creatorcontrib><creatorcontrib>Winfield, A. F. T.</creatorcontrib><creatorcontrib>Bull, L.</creatorcontrib><title>Towards imitation-enhanced Reinforcement Learning in multi-agent systems</title><title>2011 IEEE Symposium on Artificial Life (ALIFE)</title><addtitle>ALIFE</addtitle><description>Imitation, in which an individual observes and copies another's actions, is a powerful means of learning. This paper presents a way of using imitation to enhance the learning capability of individual agents. The agents employ Q-learning and we show that agents with imitation enhanced Q-learning learn faster than those with Q-learning alone.</description><subject>Actuators</subject><subject>Adaptation models</subject><subject>Electronic mail</subject><subject>Greedy algorithms</subject><subject>Learning</subject><subject>Robots</subject><subject>Watches</subject><issn>2160-6374</issn><issn>2160-6382</issn><isbn>1612840620</isbn><isbn>9781612840628</isbn><isbn>9781612840611</isbn><isbn>1612840612</isbn><isbn>9781612840635</isbn><isbn>1612840639</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo9UF9LwzAcjP_AOfsF9KVfoDO__JI0eRxjc4OCIH0faZvMyJpKE5F9eytO7-Xg7ji4I-QB6AKA6qdltdusF4wCLIQWXAp2QTJdKpDAFKcS4JLMGEhaSFTsitz9GYxe_xslvyVZjO90gpSqlHxGtvXwZcYu5r73ySQ_hMKGNxNa2-Wv1gc3jK3tbUh5Zc0YfDjkPuT95zH5whx-9HiKyfbxntw4c4w2O_Oc1Jt1vdoW1cvzbrWsCq9pKgABsJOtQNQMmgYF7xxSIRosnbDWGlBiWsO1cMwJZYRBWkrUnZJKNy3OyeNvrZ_C-4_R92Y87c-f4DcDA1C-</recordid><startdate>201104</startdate><enddate>201104</enddate><creator>Erbas, M. D.</creator><creator>Winfield, A. F. T.</creator><creator>Bull, L.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201104</creationdate><title>Towards imitation-enhanced Reinforcement Learning in multi-agent systems</title><author>Erbas, M. D. ; Winfield, A. F. T. ; Bull, L.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-13113d6c533921bb354df3055b37f5eeea185611495f2f58a5a307639d8689bc3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Actuators</topic><topic>Adaptation models</topic><topic>Electronic mail</topic><topic>Greedy algorithms</topic><topic>Learning</topic><topic>Robots</topic><topic>Watches</topic><toplevel>online_resources</toplevel><creatorcontrib>Erbas, M. D.</creatorcontrib><creatorcontrib>Winfield, A. F. T.</creatorcontrib><creatorcontrib>Bull, L.</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>Erbas, M. D.</au><au>Winfield, A. F. T.</au><au>Bull, L.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Towards imitation-enhanced Reinforcement Learning in multi-agent systems</atitle><btitle>2011 IEEE Symposium on Artificial Life (ALIFE)</btitle><stitle>ALIFE</stitle><date>2011-04</date><risdate>2011</risdate><spage>6</spage><epage>13</epage><pages>6-13</pages><issn>2160-6374</issn><eissn>2160-6382</eissn><isbn>1612840620</isbn><isbn>9781612840628</isbn><eisbn>9781612840611</eisbn><eisbn>1612840612</eisbn><eisbn>9781612840635</eisbn><eisbn>1612840639</eisbn><abstract>Imitation, in which an individual observes and copies another's actions, is a powerful means of learning. This paper presents a way of using imitation to enhance the learning capability of individual agents. The agents employ Q-learning and we show that agents with imitation enhanced Q-learning learn faster than those with Q-learning alone.</abstract><pub>IEEE</pub><doi>10.1109/ALIFE.2011.5954652</doi><tpages>8</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2160-6374 |
| ispartof | 2011 IEEE Symposium on Artificial Life (ALIFE), 2011, p.6-13 |
| issn | 2160-6374 2160-6382 |
| language | eng |
| recordid | cdi_ieee_primary_5954652 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Actuators Adaptation models Electronic mail Greedy algorithms Learning Robots Watches |
| title | Towards imitation-enhanced Reinforcement Learning in multi-agent systems |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T22%3A02%3A24IST&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=Towards%20imitation-enhanced%20Reinforcement%20Learning%20in%20multi-agent%20systems&rft.btitle=2011%20IEEE%20Symposium%20on%20Artificial%20Life%20(ALIFE)&rft.au=Erbas,%20M.%20D.&rft.date=2011-04&rft.spage=6&rft.epage=13&rft.pages=6-13&rft.issn=2160-6374&rft.eissn=2160-6382&rft.isbn=1612840620&rft.isbn_list=9781612840628&rft_id=info:doi/10.1109/ALIFE.2011.5954652&rft_dat=%3Cieee_6IE%3E5954652%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781612840611&rft.eisbn_list=1612840612&rft.eisbn_list=9781612840635&rft.eisbn_list=1612840639&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5954652&rfr_iscdi=true |