Learning to play games:
This tutorial provides a practical introduction to game strategy learning with function approximation architectures. The tutorial will cover the two main approaches to learning game strategy: evolution (including co-evolution), and temporal difference learning, and also discuss some ways of hybridiz...
Gespeichert in:
| Beteilige Person: | |
|---|---|
| Format: | Elektronisch Video |
| Sprache: | Englisch |
| Veröffentlicht: |
United States
IEEE
2010
|
| Schlagwörter: | |
| Links: | https://ieeexplore.ieee.org/courses/details/EDP172 https://ieeexplore.ieee.org/courses/details/EDP172 |
| Zusammenfassung: | This tutorial provides a practical introduction to game strategy learning with function approximation architectures. The tutorial will cover the two main approaches to learning game strategy: evolution (including co-evolution), and temporal difference learning, and also discuss some ways of hybridizing these. We also look at how the choice of input features and function approximation architecture has a critical impact on what is learned, as well as how it is interfaced to the game (e.g. as a value estimator or as an action selector). Incremental and co-evolutionary methods of learning complex skills are described. In addition to standard MLPs, attention is also given to N-Tuple systems, as these have recently shown great potential to learn quickly and effectively, and to evolutionary methods for selecting subsets of the input vector to use and neural network topologies to process it with. Each method will be demonstrated with reference to some simple fragments of software, illustrating how the learning algorithm is connected with the game and with the function approximation architecture. Example games will include Othello, Simulated Car Racing, and Ms. Pac-Man |
| Beschreibung: | Description based on online resource; title from title screen (IEEE Xplore Digital Library, viewed November 13, 2020) |
| Umfang: | 1 Online-Resource (1 Videodatei, 60 Minuten) color illustrations |
| ISBN: | 9781424461899 |
Internformat
MARC
| LEADER | 00000nam a2200000zc 4500 | ||
|---|---|---|---|
| 001 | BV047477110 | ||
| 003 | DE-604 | ||
| 005 | 20220218 | ||
| 007 | cr|uuu---uuuuu | ||
| 008 | 210921s2010 xx a||| o|||| 00||| eng d | ||
| 020 | |a 9781424461899 |9 978-1-4244-6189-9 | ||
| 035 | |a (ZDB-37-ICG)EDP172 | ||
| 035 | |a (OCoLC)1269392009 | ||
| 035 | |a (DE-599)BVBBV047477110 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-91 |a DE-92 | ||
| 082 | 0 | |a 790.1922 |2 23 | |
| 100 | 1 | |a Lucas, Simon M. |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a Learning to play games |c Simon M. Lucas |
| 264 | 1 | |a United States |b IEEE |c 2010 | |
| 300 | |a 1 Online-Resource (1 Videodatei, 60 Minuten) |b color illustrations | ||
| 336 | |b tdi |2 rdacontent | ||
| 337 | |b c |2 rdamedia | ||
| 338 | |b cr |2 rdacarrier | ||
| 500 | |a Description based on online resource; title from title screen (IEEE Xplore Digital Library, viewed November 13, 2020) | ||
| 520 | |a This tutorial provides a practical introduction to game strategy learning with function approximation architectures. The tutorial will cover the two main approaches to learning game strategy: evolution (including co-evolution), and temporal difference learning, and also discuss some ways of hybridizing these. We also look at how the choice of input features and function approximation architecture has a critical impact on what is learned, as well as how it is interfaced to the game (e.g. as a value estimator or as an action selector). Incremental and co-evolutionary methods of learning complex skills are described. In addition to standard MLPs, attention is also given to N-Tuple systems, as these have recently shown great potential to learn quickly and effectively, and to evolutionary methods for selecting subsets of the input vector to use and neural network topologies to process it with. Each method will be demonstrated with reference to some simple fragments of software, illustrating how the learning algorithm is connected with the game and with the function approximation architecture. Example games will include Othello, Simulated Car Racing, and Ms. Pac-Man | ||
| 650 | 4 | |a Games | |
| 650 | 4 | |a Computer architecture | |
| 650 | 4 | |a Standards | |
| 650 | 4 | |a Strategic planning | |
| 650 | 4 | |a Evolutionary computation | |
| 655 | 7 | |0 (DE-588)4017102-4 |a Film |2 gnd-content | |
| 912 | |a ZDB-37-ICG | ||
| 943 | 1 | |a oai:aleph.bib-bvb.de:BVB01-032878671 | |
| 966 | e | |u https://ieeexplore.ieee.org/courses/details/EDP172 |l DE-92 |p ZDB-37-ICG |x Verlag |3 Volltext | |
| 966 | e | |u https://ieeexplore.ieee.org/courses/details/EDP172 |l DE-91 |p ZDB-37-ICG |x Verlag |3 Volltext | |
Datensatz im Suchindex
| DE-BY-TUM_katkey | 2583736 |
|---|---|
| _version_ | 1821935609203130370 |
| any_adam_object | |
| author | Lucas, Simon M. |
| author_facet | Lucas, Simon M. |
| author_role | aut |
| author_sort | Lucas, Simon M. |
| author_variant | s m l sm sml |
| building | Verbundindex |
| bvnumber | BV047477110 |
| collection | ZDB-37-ICG |
| ctrlnum | (ZDB-37-ICG)EDP172 (OCoLC)1269392009 (DE-599)BVBBV047477110 |
| dewey-full | 790.1922 |
| dewey-hundreds | 700 - The arts |
| dewey-ones | 790 - Recreational and performing arts |
| dewey-raw | 790.1922 |
| dewey-search | 790.1922 |
| dewey-sort | 3790.1922 |
| dewey-tens | 790 - Recreational and performing arts |
| discipline | Sport |
| format | Electronic Video |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>02596nam a2200409zc 4500</leader><controlfield tag="001">BV047477110</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20220218 </controlfield><controlfield tag="007">cr|uuu---uuuuu</controlfield><controlfield tag="008">210921s2010 xx a||| o|||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9781424461899</subfield><subfield code="9">978-1-4244-6189-9</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ZDB-37-ICG)EDP172</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1269392009</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV047477110</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-91</subfield><subfield code="a">DE-92</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">790.1922</subfield><subfield code="2">23</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Lucas, Simon M.</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Learning to play games</subfield><subfield code="c">Simon M. Lucas</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">United States</subfield><subfield code="b">IEEE</subfield><subfield code="c">2010</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">1 Online-Resource (1 Videodatei, 60 Minuten)</subfield><subfield code="b">color illustrations</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">tdi</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">Description based on online resource; title from title screen (IEEE Xplore Digital Library, viewed November 13, 2020)</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">This tutorial provides a practical introduction to game strategy learning with function approximation architectures. The tutorial will cover the two main approaches to learning game strategy: evolution (including co-evolution), and temporal difference learning, and also discuss some ways of hybridizing these. We also look at how the choice of input features and function approximation architecture has a critical impact on what is learned, as well as how it is interfaced to the game (e.g. as a value estimator or as an action selector). Incremental and co-evolutionary methods of learning complex skills are described. In addition to standard MLPs, attention is also given to N-Tuple systems, as these have recently shown great potential to learn quickly and effectively, and to evolutionary methods for selecting subsets of the input vector to use and neural network topologies to process it with. Each method will be demonstrated with reference to some simple fragments of software, illustrating how the learning algorithm is connected with the game and with the function approximation architecture. Example games will include Othello, Simulated Car Racing, and Ms. Pac-Man</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Games</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Computer architecture</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Standards</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Strategic planning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Evolutionary computation</subfield></datafield><datafield tag="655" ind1=" " ind2="7"><subfield code="0">(DE-588)4017102-4</subfield><subfield code="a">Film</subfield><subfield code="2">gnd-content</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">ZDB-37-ICG</subfield></datafield><datafield tag="943" ind1="1" ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-032878671</subfield></datafield><datafield tag="966" ind1="e" ind2=" "><subfield code="u">https://ieeexplore.ieee.org/courses/details/EDP172</subfield><subfield code="l">DE-92</subfield><subfield code="p">ZDB-37-ICG</subfield><subfield code="x">Verlag</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="966" ind1="e" ind2=" "><subfield code="u">https://ieeexplore.ieee.org/courses/details/EDP172</subfield><subfield code="l">DE-91</subfield><subfield code="p">ZDB-37-ICG</subfield><subfield code="x">Verlag</subfield><subfield code="3">Volltext</subfield></datafield></record></collection> |
| genre | (DE-588)4017102-4 Film gnd-content |
| genre_facet | Film |
| id | DE-604.BV047477110 |
| illustrated | Illustrated |
| indexdate | 2024-12-20T19:20:37Z |
| institution | BVB |
| isbn | 9781424461899 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-032878671 |
| oclc_num | 1269392009 |
| open_access_boolean | |
| owner | DE-91 DE-BY-TUM DE-92 |
| owner_facet | DE-91 DE-BY-TUM DE-92 |
| physical | 1 Online-Resource (1 Videodatei, 60 Minuten) color illustrations |
| psigel | ZDB-37-ICG |
| publishDate | 2010 |
| publishDateSearch | 2010 |
| publishDateSort | 2010 |
| publisher | IEEE |
| record_format | marc |
| spellingShingle | Lucas, Simon M. Learning to play games Games Computer architecture Standards Strategic planning Evolutionary computation |
| subject_GND | (DE-588)4017102-4 |
| title | Learning to play games |
| title_auth | Learning to play games |
| title_exact_search | Learning to play games |
| title_full | Learning to play games Simon M. Lucas |
| title_fullStr | Learning to play games Simon M. Lucas |
| title_full_unstemmed | Learning to play games Simon M. Lucas |
| title_short | Learning to play games |
| title_sort | learning to play games |
| topic | Games Computer architecture Standards Strategic planning Evolutionary computation |
| topic_facet | Games Computer architecture Standards Strategic planning Evolutionary computation Film |
| work_keys_str_mv | AT lucassimonm learningtoplaygames |