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:
| Beteilige Person: | |
|---|---|
| Format: | E-Book |
| Sprache: | Englisch |
| Veröffentlicht: |
Cambridge, Mass.
MIT Press
©2000
|
| Schriftenreihe: | Intelligent robotics and autonomous agents series
|
| Links: | https://doi.org/10.7551/mitpress/4151.001.0001?locatt=mode:legacy |
| 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. |
| Umfang: | 1 Online-Ressource (xii, 272 Seiten) Illustrationen |
| ISBN: | 0262284448 0585228361 9780262284448 9780585228365 |
Internformat
MARC
| LEADER | 00000cam a2200000Ma 4500 | ||
|---|---|---|---|
| 001 | ZDB-260-MPOB-4151 | ||
| 003 | MaCbMITP | ||
| 005 | 20190503073311.0 | ||
| 006 | m o d | ||
| 007 | cr cn||||||||| | ||
| 008 | 000808s2000 maua ob 000 0 eng d | ||
| 020 | |a 0262284448 | ||
| 020 | |a 0585228361 | ||
| 020 | |a 9780262284448 | ||
| 020 | |a 9780585228365 | ||
| 100 | 1 | |a Stone, Peter |d 1971- | |
| 245 | 1 | 0 | |a Layered learning in multiagent systems |b a winning approach to robotic soccer |c Peter Stone |
| 264 | 1 | |a Cambridge, Mass. |b MIT Press |c ©2000 | |
| 300 | |a 1 Online-Ressource (xii, 272 Seiten) |b Illustrationen | ||
| 336 | |b txt | ||
| 337 | |b c | ||
| 338 | |b cr | ||
| 490 | 1 | |a Intelligent robotics and autonomous agents series | |
| 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. | |
| 776 | 0 | 8 | |i Erscheint auch als |n Druck-Ausgabe |z 0262194384 |
| 776 | 0 | 8 | |i Erscheint auch als |n Druck-Ausgabe |z 9780262194389 |
| 966 | 4 | 0 | |l DE-91 |p ZDB-260-MPOB |q TUM_PDA_MPOB |3 MIT Press |u https://doi.org/10.7551/mitpress/4151.001.0001?locatt=mode:legacy |3 Volltext |
| 912 | |a ZDB-260-MPOB | ||
| 912 | |a ZDB-260-MPOB | ||
| 049 | |a DE-91 | ||
Datensatz im Suchindex
| DE-BY-TUM_katkey | ZDB-260-MPOB-4151 |
|---|---|
| _version_ | 1821493840050126848 |
| adam_text | |
| any_adam_object | |
| author | Stone, Peter 1971- |
| author_facet | Stone, Peter 1971- |
| author_role | |
| author_sort | Stone, Peter 1971- |
| author_variant | p s ps |
| building | Verbundindex |
| bvnumber | localTUM |
| collection | ZDB-260-MPOB |
| format | eBook |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>02523cam a2200301Ma 4500</leader><controlfield tag="001">ZDB-260-MPOB-4151</controlfield><controlfield tag="003">MaCbMITP</controlfield><controlfield tag="005">20190503073311.0</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="020" ind1=" " ind2=" "><subfield code="a">0262284448</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">0585228361</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9780262284448</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9780585228365</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Stone, Peter</subfield><subfield code="d">1971-</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, Mass.</subfield><subfield code="b">MIT Press</subfield><subfield code="c">©2000</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">1 Online-Ressource (xii, 272 Seiten)</subfield><subfield code="b">Illustrationen</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">c</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">cr</subfield></datafield><datafield tag="490" ind1="1" ind2=" "><subfield code="a">Intelligent robotics and autonomous agents series</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="776" ind1="0" ind2="8"><subfield code="i">Erscheint auch als</subfield><subfield code="n">Druck-Ausgabe</subfield><subfield code="z">0262194384</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Erscheint auch als</subfield><subfield code="n">Druck-Ausgabe</subfield><subfield code="z">9780262194389</subfield></datafield><datafield tag="966" ind1="4" ind2="0"><subfield code="l">DE-91</subfield><subfield code="p">ZDB-260-MPOB</subfield><subfield code="q">TUM_PDA_MPOB</subfield><subfield code="3">MIT Press</subfield><subfield code="u">https://doi.org/10.7551/mitpress/4151.001.0001?locatt=mode:legacy</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">ZDB-260-MPOB</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">ZDB-260-MPOB</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-91</subfield></datafield></record></collection> |
| id | ZDB-260-MPOB-4151 |
| illustrated | Illustrated |
| indexdate | 2025-01-17T11:04:52Z |
| institution | BVB |
| isbn | 0262284448 0585228361 9780262284448 9780585228365 |
| language | English |
| open_access_boolean | |
| owner | DE-91 DE-BY-TUM |
| owner_facet | DE-91 DE-BY-TUM |
| physical | 1 Online-Ressource (xii, 272 Seiten) Illustrationen |
| psigel | ZDB-260-MPOB TUM_PDA_MPOB ZDB-260-MPOB |
| publishDate | 2000 |
| publishDateSearch | 2000 |
| publishDateSort | 2000 |
| publisher | MIT Press |
| record_format | marc |
| series2 | Intelligent robotics and autonomous agents series |
| spelling | Stone, Peter 1971- Layered learning in multiagent systems a winning approach to robotic soccer Peter Stone Cambridge, Mass. MIT Press ©2000 1 Online-Ressource (xii, 272 Seiten) Illustrationen txt c cr Intelligent robotics and autonomous agents series 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. Erscheint auch als Druck-Ausgabe 0262194384 Erscheint auch als Druck-Ausgabe 9780262194389 |
| spellingShingle | Stone, Peter 1971- Layered learning in multiagent systems a winning approach to robotic soccer |
| title | Layered learning in multiagent systems a winning approach to robotic soccer |
| 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 |
| work_keys_str_mv | AT stonepeter layeredlearninginmultiagentsystemsawinningapproachtoroboticsoccer |