Layered learning in multiagent systems :: a winning approach to robotic soccer /
This book looks at multiagent systems that consist of teams of autonomous agents acting in real-time, noisy, collaborative, and adversarial environments. The book makes four main contributions to the fields of machine learning and multiagent systems. First, it describes an architecture within which...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Elektronisch E-Book |
| Sprache: | English |
| Veröffentlicht: |
Cambridge, Massachusetts :
MIT Press,
[2000]
|
| Schriftenreihe: | Intelligent robotics and autonomous agents.
|
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Zusammenfassung: | This book looks at multiagent systems that consist of teams of autonomous agents acting in real-time, noisy, collaborative, and adversarial environments. The book makes four main contributions to the fields of machine learning and multiagent systems. First, it describes an architecture within which a flexible team structure allows member agents to decompose a task into flexible roles and to switch roles while acting. Second, it presents layered learning, a general-purpose machine-learning method for complex domains in which learning a mapping directly from agents' sensors to their actuators is intractable with existing machine-learning methods. Third, the book introduces a new multiagent reinforcement learning algorithm--team-partitioned, opaque-transition reinforcement learning (TPOT-RL)--designed for domains in which agents cannot necessarily observe the state-changes caused by other agents' actions. The final contribution is a fully functioning multiagent system that incorporates learning in a real-time, noisy domain with teammates and adversaries--a computer-simulated robotic soccer team. Peter Stone's work is the basis for the CMUnited Robotic Soccer Team, which has dominated recent RoboCup competitions. RoboCup not only helps roboticists to prove their theories in a realistic situation, but has drawn considerable public and professional attention to the field of intelligent robotics. The CMUnited team won the 1999 Stockholm simulator competition, outscoring its opponents by the rather impressive cumulative score of 110-0. |
| Beschreibung: | 1 online resource (xii, 272 pages) : illustrations |
| Bibliographie: | Includes bibliographical references (pages 261-272). |
| ISBN: | 0585228361 9780585228365 0262284448 9780262284448 |
Internformat
MARC
| LEADER | 00000cam a2200000 i 4500 | ||
|---|---|---|---|
| 001 | ZDB-4-EBU-ocm44956979 | ||
| 003 | OCoLC | ||
| 005 | 20241004212047.0 | ||
| 006 | m o d | ||
| 007 | cr cn||||||||| | ||
| 008 | 000808s2000 maua ob 000 0 eng d | ||
| 040 | |a N$T |b eng |e rda |e pn |c N$T |d OCL |d OCLCQ |d JYJ |d OCLCQ |d YDXCP |d OCLCG |d WAU |d OCLCQ |d TUU |d OCLCQ |d TNF |d OCLCQ |d VVN |d COO |d B24X7 |d IEEEE |d OCLCF |d OCLCQ |d AGLDB |d LIV |d SAV |d OCLCQ |d ICD |d QT7 |d LUE |d VTS |d OCLCQ |d INT |d TOF |d OCLCQ |d AU@ |d MITPR |d STF |d LEAUB |d JZ6 |d OL$ |d EBLCP |d CHBRC |d N$T |d IWU |d PTL |d OCLCO |d INARC |d OCLCO |d OCL |d OCLCQ |d IOY |d OCLCQ |d OCLCO |d OCLCL |d SFB |d OCLCO |d OCLCQ |d OCLCO | ||
| 019 | |a 47109487 |a 183263602 |a 490706991 |a 532573379 |a 758975362 |a 827009322 |a 868211332 |a 961618531 |a 962590146 |a 1007403023 |a 1038592729 |a 1049753302 |a 1053025482 |a 1135403622 |a 1170341068 |a 1170716580 |a 1188985827 |a 1285653597 | ||
| 020 | |a 0585228361 |q (electronic bk.) | ||
| 020 | |a 9780585228365 |q (electronic bk.) | ||
| 020 | |a 0262284448 |q (electronic bk.) | ||
| 020 | |a 9780262284448 |q (electronic bk.) | ||
| 020 | |z 0262194384 |q (hardcover ; |q alk. paper) | ||
| 020 | |z 9780262194389 | ||
| 035 | |a (OCoLC)44956979 |z (OCoLC)47109487 |z (OCoLC)183263602 |z (OCoLC)490706991 |z (OCoLC)532573379 |z (OCoLC)758975362 |z (OCoLC)827009322 |z (OCoLC)868211332 |z (OCoLC)961618531 |z (OCoLC)962590146 |z (OCoLC)1007403023 |z (OCoLC)1038592729 |z (OCoLC)1049753302 |z (OCoLC)1053025482 |z (OCoLC)1135403622 |z (OCoLC)1170341068 |z (OCoLC)1170716580 |z (OCoLC)1188985827 |z (OCoLC)1285653597 | ||
| 037 | |b 00015994 | ||
| 037 | |a 4151 |b MIT Press | ||
| 037 | |a 9780262284448 |b MIT Press | ||
| 050 | 4 | |a QA76.76.I58 |b S76 2000eb | |
| 072 | 7 | |a COM |x 005030 |2 bisacsh | |
| 072 | 7 | |a COM |x 004000 |2 bisacsh | |
| 082 | 7 | |a 006.3 |2 21 | |
| 049 | |a MAIN | ||
| 100 | 1 | |a Stone, Peter, |d 1971- |e author. |1 https://id.oclc.org/worldcat/entity/E39PCjvkRcgQytyW6TVrkGGXHP |0 http://id.loc.gov/authorities/names/n99255861 | |
| 245 | 1 | 0 | |a Layered learning in multiagent systems : |b a winning approach to robotic soccer / |c Peter Stone. |
| 264 | 1 | |a Cambridge, Massachusetts : |b MIT Press, |c [2000] | |
| 300 | |a 1 online resource (xii, 272 pages) : |b illustrations | ||
| 336 | |a text |b txt |2 rdacontent | ||
| 337 | |a computer |b c |2 rdamedia | ||
| 338 | |a online resource |b cr |2 rdacarrier | ||
| 490 | 1 | |a Intelligent robotics and autonomous agents series | |
| 504 | |a Includes bibliographical references (pages 261-272). | ||
| 588 | 0 | |a Online resource; title from PDF title page (EBSCOHost, viewed September 29, 2020). | |
| 505 | 0 | 0 | |g Introduction -- |t Substrate systems -- |t Team member agent architecture -- |t Layered learning -- |t Learning an individual skill -- |t Learning a multiagent behavior -- |t Learning a team behavior -- |t Competition results -- |t Related work -- |t Conclusions and future work. |
| 520 | 8 | |a This book looks at multiagent systems that consist of teams of autonomous agents acting in real-time, noisy, collaborative, and adversarial environments. The book makes four main contributions to the fields of machine learning and multiagent systems. First, it describes an architecture within which a flexible team structure allows member agents to decompose a task into flexible roles and to switch roles while acting. Second, it presents layered learning, a general-purpose machine-learning method for complex domains in which learning a mapping directly from agents' sensors to their actuators is intractable with existing machine-learning methods. Third, the book introduces a new multiagent reinforcement learning algorithm--team-partitioned, opaque-transition reinforcement learning (TPOT-RL)--designed for domains in which agents cannot necessarily observe the state-changes caused by other agents' actions. The final contribution is a fully functioning multiagent system that incorporates learning in a real-time, noisy domain with teammates and adversaries--a computer-simulated robotic soccer team. Peter Stone's work is the basis for the CMUnited Robotic Soccer Team, which has dominated recent RoboCup competitions. RoboCup not only helps roboticists to prove their theories in a realistic situation, but has drawn considerable public and professional attention to the field of intelligent robotics. The CMUnited team won the 1999 Stockholm simulator competition, outscoring its opponents by the rather impressive cumulative score of 110-0. | |
| 650 | 0 | |a Multiagent systems. |0 http://id.loc.gov/authorities/subjects/sh2009010910 | |
| 650 | 0 | |a Robotics. |0 http://id.loc.gov/authorities/subjects/sh85114628 | |
| 650 | 0 | |a Intelligent agents (Computer software) |0 http://id.loc.gov/authorities/subjects/sh97000493 | |
| 650 | 2 | |a Robotics |0 https://id.nlm.nih.gov/mesh/D012371 | |
| 650 | 6 | |a Robotique. | |
| 650 | 6 | |a Agents intelligents (Logiciels) | |
| 650 | 6 | |a Systèmes multiagents (Intelligence artificielle) | |
| 650 | 7 | |a COMPUTERS |x Enterprise Applications |x Business Intelligence Tools. |2 bisacsh | |
| 650 | 7 | |a COMPUTERS |x Intelligence (AI) & Semantics. |2 bisacsh | |
| 650 | 7 | |a Intelligent agents (Computer software) |2 fast | |
| 650 | 7 | |a Multiagent systems |2 fast | |
| 650 | 7 | |a Robotics |2 fast | |
| 650 | 7 | |a SISTEMAS MULTIAGENTES. |2 larpcal | |
| 653 | |a COMPUTER SCIENCE/Robotics & Agents | ||
| 653 | |a ARCHITECTURE/General | ||
| 758 | |i has work: |a Layered learning in multiagent systems (Text) |1 https://id.oclc.org/worldcat/entity/E39PCFB9Pck74PmmQGqhxGdBpq |4 https://id.oclc.org/worldcat/ontology/hasWork | ||
| 776 | 0 | 8 | |i Print version: |a Stone, Peter, 1971- |t Layered learning in multiagent systems. |d Cambridge, Mass. : MIT Press, ©2000 |z 0262194384 |w (DLC) 99049153 |w (OCoLC)42641656 |
| 830 | 0 | |a Intelligent robotics and autonomous agents. |0 http://id.loc.gov/authorities/names/n98024999 | |
| 856 | 4 | 0 | |l FWS01 |p ZDB-4-EBU |q FWS_PDA_EBU |u https://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&AN=32636 |3 Volltext |
| 936 | |a BATCHLOAD | ||
| 938 | |a Books 24x7 |b B247 |n bks00001066 | ||
| 938 | |a ProQuest Ebook Central |b EBLB |n EBL5966225 | ||
| 938 | |a EBSCOhost |b EBSC |n 32636 | ||
| 938 | |a IEEE |b IEEE |n 6267440 | ||
| 938 | |a Internet Archive |b INAR |n layeredlearningi0000ston | ||
| 938 | |a YBP Library Services |b YANK |n 2314714 | ||
| 938 | |a YBP Library Services |b YANK |n 10835680 | ||
| 994 | |a 92 |b GEBAY | ||
| 912 | |a ZDB-4-EBU | ||
| 049 | |a DE-863 | ||
Datensatz im Suchindex
| DE-BY-FWS_katkey | ZDB-4-EBU-ocm44956979 |
|---|---|
| _version_ | 1816796894071881728 |
| adam_text | |
| any_adam_object | |
| author | Stone, Peter, 1971- |
| author_GND | http://id.loc.gov/authorities/names/n99255861 |
| author_facet | Stone, Peter, 1971- |
| author_role | aut |
| author_sort | Stone, Peter, 1971- |
| author_variant | p s ps |
| building | Verbundindex |
| bvnumber | localFWS |
| callnumber-first | Q - Science |
| callnumber-label | QA76 |
| callnumber-raw | QA76.76.I58 S76 2000eb |
| callnumber-search | QA76.76.I58 S76 2000eb |
| callnumber-sort | QA 276.76 I58 S76 42000EB |
| callnumber-subject | QA - Mathematics |
| collection | ZDB-4-EBU |
| contents | Substrate systems -- Team member agent architecture -- Layered learning -- Learning an individual skill -- Learning a multiagent behavior -- Learning a team behavior -- Competition results -- Related work -- Conclusions and future work. |
| ctrlnum | (OCoLC)44956979 |
| dewey-full | 006.3 |
| dewey-hundreds | 000 - Computer science, information, general works |
| dewey-ones | 006 - Special computer methods |
| dewey-raw | 006.3 |
| dewey-search | 006.3 |
| dewey-sort | 16.3 |
| dewey-tens | 000 - Computer science, information, general works |
| discipline | Informatik |
| format | Electronic eBook |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>06163cam a2200781 i 4500</leader><controlfield tag="001">ZDB-4-EBU-ocm44956979 </controlfield><controlfield tag="003">OCoLC</controlfield><controlfield tag="005">20241004212047.0</controlfield><controlfield tag="006">m o d </controlfield><controlfield tag="007">cr cn|||||||||</controlfield><controlfield tag="008">000808s2000 maua ob 000 0 eng d</controlfield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">N$T</subfield><subfield code="b">eng</subfield><subfield code="e">rda</subfield><subfield code="e">pn</subfield><subfield code="c">N$T</subfield><subfield code="d">OCL</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">JYJ</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">YDXCP</subfield><subfield code="d">OCLCG</subfield><subfield code="d">WAU</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">TUU</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">TNF</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">VVN</subfield><subfield code="d">COO</subfield><subfield code="d">B24X7</subfield><subfield code="d">IEEEE</subfield><subfield code="d">OCLCF</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">AGLDB</subfield><subfield code="d">LIV</subfield><subfield code="d">SAV</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">ICD</subfield><subfield code="d">QT7</subfield><subfield code="d">LUE</subfield><subfield code="d">VTS</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">INT</subfield><subfield code="d">TOF</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">AU@</subfield><subfield code="d">MITPR</subfield><subfield code="d">STF</subfield><subfield code="d">LEAUB</subfield><subfield code="d">JZ6</subfield><subfield code="d">OL$</subfield><subfield code="d">EBLCP</subfield><subfield code="d">CHBRC</subfield><subfield code="d">N$T</subfield><subfield code="d">IWU</subfield><subfield code="d">PTL</subfield><subfield code="d">OCLCO</subfield><subfield code="d">INARC</subfield><subfield code="d">OCLCO</subfield><subfield code="d">OCL</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">IOY</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">OCLCO</subfield><subfield code="d">OCLCL</subfield><subfield code="d">SFB</subfield><subfield code="d">OCLCO</subfield><subfield code="d">OCLCQ</subfield><subfield code="d">OCLCO</subfield></datafield><datafield tag="019" ind1=" " ind2=" "><subfield code="a">47109487</subfield><subfield code="a">183263602</subfield><subfield code="a">490706991</subfield><subfield code="a">532573379</subfield><subfield code="a">758975362</subfield><subfield code="a">827009322</subfield><subfield code="a">868211332</subfield><subfield code="a">961618531</subfield><subfield code="a">962590146</subfield><subfield code="a">1007403023</subfield><subfield code="a">1038592729</subfield><subfield code="a">1049753302</subfield><subfield code="a">1053025482</subfield><subfield code="a">1135403622</subfield><subfield code="a">1170341068</subfield><subfield code="a">1170716580</subfield><subfield code="a">1188985827</subfield><subfield code="a">1285653597</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">0585228361</subfield><subfield code="q">(electronic bk.)</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9780585228365</subfield><subfield code="q">(electronic bk.)</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">0262284448</subfield><subfield code="q">(electronic bk.)</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9780262284448</subfield><subfield code="q">(electronic bk.)</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="z">0262194384</subfield><subfield code="q">(hardcover ;</subfield><subfield code="q">alk. paper)</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="z">9780262194389</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)44956979</subfield><subfield code="z">(OCoLC)47109487</subfield><subfield code="z">(OCoLC)183263602</subfield><subfield code="z">(OCoLC)490706991</subfield><subfield code="z">(OCoLC)532573379</subfield><subfield code="z">(OCoLC)758975362</subfield><subfield code="z">(OCoLC)827009322</subfield><subfield code="z">(OCoLC)868211332</subfield><subfield code="z">(OCoLC)961618531</subfield><subfield code="z">(OCoLC)962590146</subfield><subfield code="z">(OCoLC)1007403023</subfield><subfield code="z">(OCoLC)1038592729</subfield><subfield code="z">(OCoLC)1049753302</subfield><subfield code="z">(OCoLC)1053025482</subfield><subfield code="z">(OCoLC)1135403622</subfield><subfield code="z">(OCoLC)1170341068</subfield><subfield code="z">(OCoLC)1170716580</subfield><subfield code="z">(OCoLC)1188985827</subfield><subfield code="z">(OCoLC)1285653597</subfield></datafield><datafield tag="037" ind1=" " ind2=" "><subfield code="b">00015994</subfield></datafield><datafield tag="037" ind1=" " ind2=" "><subfield code="a">4151</subfield><subfield code="b">MIT Press</subfield></datafield><datafield tag="037" ind1=" " ind2=" "><subfield code="a">9780262284448</subfield><subfield code="b">MIT Press</subfield></datafield><datafield tag="050" ind1=" " ind2="4"><subfield code="a">QA76.76.I58</subfield><subfield code="b">S76 2000eb</subfield></datafield><datafield tag="072" ind1=" " ind2="7"><subfield code="a">COM</subfield><subfield code="x">005030</subfield><subfield code="2">bisacsh</subfield></datafield><datafield tag="072" ind1=" " ind2="7"><subfield code="a">COM</subfield><subfield code="x">004000</subfield><subfield code="2">bisacsh</subfield></datafield><datafield tag="082" ind1="7" ind2=" "><subfield code="a">006.3</subfield><subfield code="2">21</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">MAIN</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Stone, Peter,</subfield><subfield code="d">1971-</subfield><subfield code="e">author.</subfield><subfield code="1">https://id.oclc.org/worldcat/entity/E39PCjvkRcgQytyW6TVrkGGXHP</subfield><subfield code="0">http://id.loc.gov/authorities/names/n99255861</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Layered learning in multiagent systems :</subfield><subfield code="b">a winning approach to robotic soccer /</subfield><subfield code="c">Peter Stone.</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Cambridge, Massachusetts :</subfield><subfield code="b">MIT Press,</subfield><subfield code="c">[2000]</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">1 online resource (xii, 272 pages) :</subfield><subfield code="b">illustrations</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">computer</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">online resource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="1" ind2=" "><subfield code="a">Intelligent robotics and autonomous agents series</subfield></datafield><datafield tag="504" ind1=" " ind2=" "><subfield code="a">Includes bibliographical references (pages 261-272).</subfield></datafield><datafield tag="588" ind1="0" ind2=" "><subfield code="a">Online resource; title from PDF title page (EBSCOHost, viewed September 29, 2020).</subfield></datafield><datafield tag="505" ind1="0" ind2="0"><subfield code="g">Introduction --</subfield><subfield code="t">Substrate systems --</subfield><subfield code="t">Team member agent architecture --</subfield><subfield code="t">Layered learning --</subfield><subfield code="t">Learning an individual skill --</subfield><subfield code="t">Learning a multiagent behavior --</subfield><subfield code="t">Learning a team behavior --</subfield><subfield code="t">Competition results --</subfield><subfield code="t">Related work --</subfield><subfield code="t">Conclusions and future work.</subfield></datafield><datafield tag="520" ind1="8" ind2=" "><subfield code="a">This book looks at multiagent systems that consist of teams of autonomous agents acting in real-time, noisy, collaborative, and adversarial environments. The book makes four main contributions to the fields of machine learning and multiagent systems. First, it describes an architecture within which a flexible team structure allows member agents to decompose a task into flexible roles and to switch roles while acting. Second, it presents layered learning, a general-purpose machine-learning method for complex domains in which learning a mapping directly from agents' sensors to their actuators is intractable with existing machine-learning methods. Third, the book introduces a new multiagent reinforcement learning algorithm--team-partitioned, opaque-transition reinforcement learning (TPOT-RL)--designed for domains in which agents cannot necessarily observe the state-changes caused by other agents' actions. The final contribution is a fully functioning multiagent system that incorporates learning in a real-time, noisy domain with teammates and adversaries--a computer-simulated robotic soccer team. Peter Stone's work is the basis for the CMUnited Robotic Soccer Team, which has dominated recent RoboCup competitions. RoboCup not only helps roboticists to prove their theories in a realistic situation, but has drawn considerable public and professional attention to the field of intelligent robotics. The CMUnited team won the 1999 Stockholm simulator competition, outscoring its opponents by the rather impressive cumulative score of 110-0.</subfield></datafield><datafield tag="650" ind1=" " ind2="0"><subfield code="a">Multiagent systems.</subfield><subfield code="0">http://id.loc.gov/authorities/subjects/sh2009010910</subfield></datafield><datafield tag="650" ind1=" " ind2="0"><subfield code="a">Robotics.</subfield><subfield code="0">http://id.loc.gov/authorities/subjects/sh85114628</subfield></datafield><datafield tag="650" ind1=" " ind2="0"><subfield code="a">Intelligent agents (Computer software)</subfield><subfield code="0">http://id.loc.gov/authorities/subjects/sh97000493</subfield></datafield><datafield tag="650" ind1=" " ind2="2"><subfield code="a">Robotics</subfield><subfield code="0">https://id.nlm.nih.gov/mesh/D012371</subfield></datafield><datafield tag="650" ind1=" " ind2="6"><subfield code="a">Robotique.</subfield></datafield><datafield tag="650" ind1=" " ind2="6"><subfield code="a">Agents intelligents (Logiciels)</subfield></datafield><datafield tag="650" ind1=" " ind2="6"><subfield code="a">Systèmes multiagents (Intelligence artificielle)</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">COMPUTERS</subfield><subfield code="x">Enterprise Applications</subfield><subfield code="x">Business Intelligence Tools.</subfield><subfield code="2">bisacsh</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">COMPUTERS</subfield><subfield code="x">Intelligence (AI) & Semantics.</subfield><subfield code="2">bisacsh</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Intelligent agents (Computer software)</subfield><subfield code="2">fast</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Multiagent systems</subfield><subfield code="2">fast</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Robotics</subfield><subfield code="2">fast</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">SISTEMAS MULTIAGENTES.</subfield><subfield code="2">larpcal</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">COMPUTER SCIENCE/Robotics & Agents</subfield></datafield><datafield tag="653" ind1=" " ind2=" "><subfield code="a">ARCHITECTURE/General</subfield></datafield><datafield tag="758" ind1=" " ind2=" "><subfield code="i">has work:</subfield><subfield code="a">Layered learning in multiagent systems (Text)</subfield><subfield code="1">https://id.oclc.org/worldcat/entity/E39PCFB9Pck74PmmQGqhxGdBpq</subfield><subfield code="4">https://id.oclc.org/worldcat/ontology/hasWork</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Print version:</subfield><subfield code="a">Stone, Peter, 1971-</subfield><subfield code="t">Layered learning in multiagent systems.</subfield><subfield code="d">Cambridge, Mass. : MIT Press, ©2000</subfield><subfield code="z">0262194384</subfield><subfield code="w">(DLC) 99049153</subfield><subfield code="w">(OCoLC)42641656</subfield></datafield><datafield tag="830" ind1=" " ind2="0"><subfield code="a">Intelligent robotics and autonomous agents.</subfield><subfield code="0">http://id.loc.gov/authorities/names/n98024999</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="l">FWS01</subfield><subfield code="p">ZDB-4-EBU</subfield><subfield code="q">FWS_PDA_EBU</subfield><subfield code="u">https://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&AN=32636</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="936" ind1=" " ind2=" "><subfield code="a">BATCHLOAD</subfield></datafield><datafield tag="938" ind1=" " ind2=" "><subfield code="a">Books 24x7</subfield><subfield code="b">B247</subfield><subfield code="n">bks00001066</subfield></datafield><datafield tag="938" ind1=" " ind2=" "><subfield code="a">ProQuest Ebook Central</subfield><subfield code="b">EBLB</subfield><subfield code="n">EBL5966225</subfield></datafield><datafield tag="938" ind1=" " ind2=" "><subfield code="a">EBSCOhost</subfield><subfield code="b">EBSC</subfield><subfield code="n">32636</subfield></datafield><datafield tag="938" ind1=" " ind2=" "><subfield code="a">IEEE</subfield><subfield code="b">IEEE</subfield><subfield code="n">6267440</subfield></datafield><datafield tag="938" ind1=" " ind2=" "><subfield code="a">Internet Archive</subfield><subfield code="b">INAR</subfield><subfield code="n">layeredlearningi0000ston</subfield></datafield><datafield tag="938" ind1=" " ind2=" "><subfield code="a">YBP Library Services</subfield><subfield code="b">YANK</subfield><subfield code="n">2314714</subfield></datafield><datafield tag="938" ind1=" " ind2=" "><subfield code="a">YBP Library Services</subfield><subfield code="b">YANK</subfield><subfield code="n">10835680</subfield></datafield><datafield tag="994" ind1=" " ind2=" "><subfield code="a">92</subfield><subfield code="b">GEBAY</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">ZDB-4-EBU</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-863</subfield></datafield></record></collection> |
| id | ZDB-4-EBU-ocm44956979 |
| illustrated | Illustrated |
| indexdate | 2024-11-26T14:48:55Z |
| institution | BVB |
| isbn | 0585228361 9780585228365 0262284448 9780262284448 |
| language | English |
| oclc_num | 44956979 |
| open_access_boolean | |
| owner | MAIN DE-863 DE-BY-FWS |
| owner_facet | MAIN DE-863 DE-BY-FWS |
| physical | 1 online resource (xii, 272 pages) : illustrations |
| psigel | ZDB-4-EBU |
| publishDate | 2000 |
| publishDateSearch | 2000 |
| publishDateSort | 2000 |
| publisher | MIT Press, |
| record_format | marc |
| series | Intelligent robotics and autonomous agents. |
| series2 | Intelligent robotics and autonomous agents series |
| spelling | Stone, Peter, 1971- author. https://id.oclc.org/worldcat/entity/E39PCjvkRcgQytyW6TVrkGGXHP http://id.loc.gov/authorities/names/n99255861 Layered learning in multiagent systems : a winning approach to robotic soccer / Peter Stone. Cambridge, Massachusetts : MIT Press, [2000] 1 online resource (xii, 272 pages) : illustrations text txt rdacontent computer c rdamedia online resource cr rdacarrier Intelligent robotics and autonomous agents series Includes bibliographical references (pages 261-272). Online resource; title from PDF title page (EBSCOHost, viewed September 29, 2020). Introduction -- Substrate systems -- Team member agent architecture -- Layered learning -- Learning an individual skill -- Learning a multiagent behavior -- Learning a team behavior -- Competition results -- Related work -- Conclusions and future work. This book looks at multiagent systems that consist of teams of autonomous agents acting in real-time, noisy, collaborative, and adversarial environments. The book makes four main contributions to the fields of machine learning and multiagent systems. First, it describes an architecture within which a flexible team structure allows member agents to decompose a task into flexible roles and to switch roles while acting. Second, it presents layered learning, a general-purpose machine-learning method for complex domains in which learning a mapping directly from agents' sensors to their actuators is intractable with existing machine-learning methods. Third, the book introduces a new multiagent reinforcement learning algorithm--team-partitioned, opaque-transition reinforcement learning (TPOT-RL)--designed for domains in which agents cannot necessarily observe the state-changes caused by other agents' actions. The final contribution is a fully functioning multiagent system that incorporates learning in a real-time, noisy domain with teammates and adversaries--a computer-simulated robotic soccer team. Peter Stone's work is the basis for the CMUnited Robotic Soccer Team, which has dominated recent RoboCup competitions. RoboCup not only helps roboticists to prove their theories in a realistic situation, but has drawn considerable public and professional attention to the field of intelligent robotics. The CMUnited team won the 1999 Stockholm simulator competition, outscoring its opponents by the rather impressive cumulative score of 110-0. Multiagent systems. http://id.loc.gov/authorities/subjects/sh2009010910 Robotics. http://id.loc.gov/authorities/subjects/sh85114628 Intelligent agents (Computer software) http://id.loc.gov/authorities/subjects/sh97000493 Robotics https://id.nlm.nih.gov/mesh/D012371 Robotique. Agents intelligents (Logiciels) Systèmes multiagents (Intelligence artificielle) COMPUTERS Enterprise Applications Business Intelligence Tools. bisacsh COMPUTERS Intelligence (AI) & Semantics. bisacsh Intelligent agents (Computer software) fast Multiagent systems fast Robotics fast SISTEMAS MULTIAGENTES. larpcal COMPUTER SCIENCE/Robotics & Agents ARCHITECTURE/General has work: Layered learning in multiagent systems (Text) https://id.oclc.org/worldcat/entity/E39PCFB9Pck74PmmQGqhxGdBpq https://id.oclc.org/worldcat/ontology/hasWork Print version: Stone, Peter, 1971- Layered learning in multiagent systems. Cambridge, Mass. : MIT Press, ©2000 0262194384 (DLC) 99049153 (OCoLC)42641656 Intelligent robotics and autonomous agents. http://id.loc.gov/authorities/names/n98024999 FWS01 ZDB-4-EBU FWS_PDA_EBU https://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&AN=32636 Volltext |
| spellingShingle | Stone, Peter, 1971- Layered learning in multiagent systems : a winning approach to robotic soccer / Intelligent robotics and autonomous agents. Substrate systems -- Team member agent architecture -- Layered learning -- Learning an individual skill -- Learning a multiagent behavior -- Learning a team behavior -- Competition results -- Related work -- Conclusions and future work. Multiagent systems. http://id.loc.gov/authorities/subjects/sh2009010910 Robotics. http://id.loc.gov/authorities/subjects/sh85114628 Intelligent agents (Computer software) http://id.loc.gov/authorities/subjects/sh97000493 Robotics https://id.nlm.nih.gov/mesh/D012371 Robotique. Agents intelligents (Logiciels) Systèmes multiagents (Intelligence artificielle) COMPUTERS Enterprise Applications Business Intelligence Tools. bisacsh COMPUTERS Intelligence (AI) & Semantics. bisacsh Intelligent agents (Computer software) fast Multiagent systems fast Robotics fast SISTEMAS MULTIAGENTES. larpcal |
| subject_GND | http://id.loc.gov/authorities/subjects/sh2009010910 http://id.loc.gov/authorities/subjects/sh85114628 http://id.loc.gov/authorities/subjects/sh97000493 https://id.nlm.nih.gov/mesh/D012371 |
| title | Layered learning in multiagent systems : a winning approach to robotic soccer / |
| title_alt | Substrate systems -- Team member agent architecture -- Layered learning -- Learning an individual skill -- Learning a multiagent behavior -- Learning a team behavior -- Competition results -- Related work -- Conclusions and future work. |
| title_auth | Layered learning in multiagent systems : a winning approach to robotic soccer / |
| title_exact_search | Layered learning in multiagent systems : a winning approach to robotic soccer / |
| title_full | Layered learning in multiagent systems : a winning approach to robotic soccer / Peter Stone. |
| title_fullStr | Layered learning in multiagent systems : a winning approach to robotic soccer / Peter Stone. |
| title_full_unstemmed | Layered learning in multiagent systems : a winning approach to robotic soccer / Peter Stone. |
| title_short | Layered learning in multiagent systems : |
| title_sort | layered learning in multiagent systems a winning approach to robotic soccer |
| title_sub | a winning approach to robotic soccer / |
| topic | Multiagent systems. http://id.loc.gov/authorities/subjects/sh2009010910 Robotics. http://id.loc.gov/authorities/subjects/sh85114628 Intelligent agents (Computer software) http://id.loc.gov/authorities/subjects/sh97000493 Robotics https://id.nlm.nih.gov/mesh/D012371 Robotique. Agents intelligents (Logiciels) Systèmes multiagents (Intelligence artificielle) COMPUTERS Enterprise Applications Business Intelligence Tools. bisacsh COMPUTERS Intelligence (AI) & Semantics. bisacsh Intelligent agents (Computer software) fast Multiagent systems fast Robotics fast SISTEMAS MULTIAGENTES. larpcal |
| topic_facet | Multiagent systems. Robotics. Intelligent agents (Computer software) Robotics Robotique. Agents intelligents (Logiciels) Systèmes multiagents (Intelligence artificielle) COMPUTERS Enterprise Applications Business Intelligence Tools. COMPUTERS Intelligence (AI) & Semantics. Multiagent systems SISTEMAS MULTIAGENTES. |
| url | https://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&AN=32636 |
| work_keys_str_mv | AT stonepeter layeredlearninginmultiagentsystemsawinningapproachtoroboticsoccer |