Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Dennis J.N.J. Soemers"'
Publikováno v:
Information Sciences, 624, 277-298. Elsevier Inc.
Local, spatial state-action features can be used to effectively train linear policies from self-play in a wide variety of board games. Such policies can play games directly, or be used to bias tree search agents. However, the resulting feature sets c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0c2779a56a8bab842bd7f211fe3f2b65
https://cris.maastrichtuniversity.nl/en/publications/389773e7-8f9f-4f59-9ac8-336219c9c755
https://cris.maastrichtuniversity.nl/en/publications/389773e7-8f9f-4f59-9ac8-336219c9c755
Publikováno v:
Artificial Intelligence, 321:103937. Elsevier Science
arXiv pre
arXiv pre
In many board games and other abstract games, patterns have been used as features that can guide automated game-playing agents. Such patterns or features often represent particular configurations of pieces, empty positions, etc., which may be relevan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dc5d1a5a72d54621531222adbb371904
Publikováno v:
ICGA Journal, 44(2), 56-66. IOS Press
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1f74488b46d37f468b665a7dbd807151
https://cris.maastrichtuniversity.nl/en/publications/584e4977-21b8-4867-8bce-8a9831a7e148
https://cris.maastrichtuniversity.nl/en/publications/584e4977-21b8-4867-8bce-8a9831a7e148
