Výsledky vyhledávání - "Mark H. M. Winands"

Analysis of the Impact of Randomization of Search-Control Parameters in Monte-Carlo Tree Search

Autor: Mark H. M. Winands, Chiara F. Sironi

Publikováno v: Journal of Artificial Intelligence Research, 72, 717-757. AI Access Foundation

Monte-Carlo Tree Search (MCTS) has been applied successfully in many domains, including games. However, its performance is not uniform on all domains, and it also depends on how parameters that control the search are set. Parameter values that are op

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::34d117a43361d82a6df15536ed6ed5ec
https://doi.org/10.1613/jair.1.12065

Zobrazit plný text záznamu

Enhancing Playout Policy Adaptation for General Game Playing

Autor: Mark H. M. Winands, Chiara F. Sironi, Tristan Cazenave

Publikováno v: Monte Carlo Search: MCS 2020, 116-139
STARTPAGE=116;ENDPAGE=139;TITLE=Monte Carlo Search
Communications in Computer and Information Science ISBN: 9783030894528

Playout policy adaptation (ppa) is a state-of-the-art strategy that has been proposed to control the playouts in monte-carlo tree search (mcts). Ppa has been successfully applied to many two-player, sequential-move games. This paper further evaluates

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b24e7e2680dc991fd0a7023ff4b64714
https://doi.org/10.1007/978-3-030-89453-5_9

Zobrazit plný text záznamu

Monte Carlo Tree Search as an intelligent search tool in structural design problems

Autor: L. Rossi, Mark H. M. Winands, Christoph Butenweg

Publikováno v: Engineering with Computers, 38(4). Springer
Engineering with computers 38(4), 3219-3236 (2022). doi:10.1007/s00366-021-01338-2

Engineering with computers (2021). doi:10.1007/s00366-021-01338-2
Published by Springer, London

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::59c103bdc138a444729585842a589a20
https://doi.org/10.1007/s00366-021-01338-2

Zobrazit plný text záznamu

Adaptive General Search Framework for Games and Beyond

Autor: Chiara F. Sironi, Mark H. M. Winands

Publikováno v: 2021 IEEE Conference on Games (CoG), 1051-1058
STARTPAGE=1051;ENDPAGE=1058;TITLE=2021 IEEE Conference on Games (CoG)

The research field of Artificial General Intelligence (AGI) is concerned with the creation of adaptive programs that can autonomously address tasks of a different nature. Search and planning have been identified as core capabilities of AGI, and have

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1839d1cc5425d6b65985b037250858fc
https://cris.maastrichtuniversity.nl/en/publications/d5b47367-c519-403a-8695-36cac866df09

Zobrazit plný text záznamu

Comparing Randomization Strategies for Search-Control Parameters in Monte-Carlo Tree Search

Autor: Mark H. M. Winands, Chiara F. Sironi

Publikováno v: 2019 IEEE Conference on Games (CoG), 1-8
STARTPAGE=1;ENDPAGE=8;TITLE=2019 IEEE Conference on Games (CoG)
CoG

Monte-Carlo Tree Search (MCTS) has been applied successfully in many domains. Previous research has shown that adding randomization to certain components of MCTS might increase the diversification of the search and improve the performance. In a domai

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::001b6ba77c3144d63e65efa8b23a80ac
https://ieeexplore.ieee.org/document/8848056/

Zobrazit plný text záznamu

Self-Adaptive Rolling Horizon Evolutionary Algorithms for General Video Game Playing

Autor: Raluca D. Gaina, Simon M. Lucas, Diego Perez-Liebana, Mark H. M. Winands, Chiara F. Sironi

Publikováno v: CoG
2020 IEEE Conference on Games (CoG), 367-374
STARTPAGE=367;ENDPAGE=374;TITLE=2020 IEEE Conference on Games (CoG)

For general video game playing agents, the biggest challenge is adapting to the wide variety of situations they encounter and responding appropriately. Some success was recently achieved by modifying search-control parameters in agents on-line, durin

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e992cafdaa77163b92c40bcc41f65652
https://doi.org/10.1109/CoG47356.2020.9231587

Zobrazit plný text záznamu

Self-Adaptive Monte Carlo Tree Search in General Game Playing

Autor: Chiara F. Sironi, Mark H. M. Winands, Jialin Liu

Publikováno v: IEEE Transactions on Games, 12(2), 132-144. IEEE

Many enhancements for Monte Carlo tree search (MCTS) have been applied successfully in general game playing (GGP). MCTS and its enhancements are controlled by multiple parameters that require extensive and time-consuming offline optimization. Moreove

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d3b51f783399bdad0160ccfa190b7207
https://cris.maastrichtuniversity.nl/en/publications/dc999e7f-896a-4e4d-bfa6-346ecc8db2fa

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání