深度学习一般游戏玩与Ludii和Polygames

Dennis J. N. J. Soemers, Vegard Mella, C. Browne, O. Teytaud
{"title":"深度学习一般游戏玩与Ludii和Polygames","authors":"Dennis J. N. J. Soemers, Vegard Mella, C. Browne, O. Teytaud","doi":"10.3233/icg-220197","DOIUrl":null,"url":null,"abstract":"Combinations of Monte-Carlo tree search and Deep Neural Networks, trained through self-play, have produced state-of-the-art results for automated game-playing in many board games. The training and search algorithms are not game-specific, but every individual game that these approaches are applied to still requires domain knowledge for the implementation of the game’s rules, and constructing the neural network’s architecture – in particular the shapes of its input and output tensors. Ludii is a general game system that already contains over 1,000 different games, which can rapidly grow thanks to its powerful and user-friendly game description language. Polygames is a framework with training and search algorithms, which has already produced superhuman players for several board games. This paper describes the implementation of a bridge between Ludii and Polygames, which enables Polygames to train and evaluate models for games that are implemented and run through Ludii. We do not require any game-specific domain knowledge anymore, and instead leverage our domain knowledge of the Ludii system and its abstract state and move representations to write functions that can automatically determine the appropriate shapes for input and output tensors for any game implemented in Ludii. We describe experimental results for short training runs in a wide variety of different board games, and discuss several open problems and avenues for future research.","PeriodicalId":14829,"journal":{"name":"J. Int. Comput. Games Assoc.","volume":"19 1","pages":"146-161"},"PeriodicalIF":0.0000,"publicationDate":"2021-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":"{\"title\":\"Deep Learning for General Game Playing with Ludii and Polygames\",\"authors\":\"Dennis J. N. J. Soemers, Vegard Mella, C. Browne, O. Teytaud\",\"doi\":\"10.3233/icg-220197\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Combinations of Monte-Carlo tree search and Deep Neural Networks, trained through self-play, have produced state-of-the-art results for automated game-playing in many board games. The training and search algorithms are not game-specific, but every individual game that these approaches are applied to still requires domain knowledge for the implementation of the game’s rules, and constructing the neural network’s architecture – in particular the shapes of its input and output tensors. Ludii is a general game system that already contains over 1,000 different games, which can rapidly grow thanks to its powerful and user-friendly game description language. Polygames is a framework with training and search algorithms, which has already produced superhuman players for several board games. This paper describes the implementation of a bridge between Ludii and Polygames, which enables Polygames to train and evaluate models for games that are implemented and run through Ludii. We do not require any game-specific domain knowledge anymore, and instead leverage our domain knowledge of the Ludii system and its abstract state and move representations to write functions that can automatically determine the appropriate shapes for input and output tensors for any game implemented in Ludii. We describe experimental results for short training runs in a wide variety of different board games, and discuss several open problems and avenues for future research.\",\"PeriodicalId\":14829,\"journal\":{\"name\":\"J. Int. Comput. Games Assoc.\",\"volume\":\"19 1\",\"pages\":\"146-161\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-01-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"8\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"J. Int. Comput. Games Assoc.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3233/icg-220197\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"J. Int. Comput. Games Assoc.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3233/icg-220197","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8

摘要

蒙特卡罗树搜索和深度神经网络的结合,通过自我游戏训练,已经在许多棋盘游戏中产生了最先进的自动游戏结果。训练和搜索算法并不是特定于游戏的,但是应用这些方法的每一个游戏仍然需要领域知识来实现游戏规则,并构建神经网络的架构——特别是它的输入和输出张量的形状。Ludii是一个通用的游戏系统,已经包含了超过1000种不同的游戏,由于其强大而友好的游戏描述语言,它可以迅速增长。Polygames是一个带有训练和搜索算法的框架,它已经为一些桌游创造了超人玩家。本文描述了Ludii和Polygames之间的桥梁的实现,它使Polygames能够训练和评估通过Ludii实现和运行的游戏模型。我们不再需要任何特定于游戏的领域知识,而是利用我们对Ludii系统的领域知识及其抽象状态和移动表示来编写函数,这些函数可以自动确定在Ludii中实现的任何游戏的输入和输出张量的适当形状。我们描述了在各种不同的棋盘游戏中进行短期训练的实验结果,并讨论了几个开放的问题和未来研究的途径。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Deep Learning for General Game Playing with Ludii and Polygames
Combinations of Monte-Carlo tree search and Deep Neural Networks, trained through self-play, have produced state-of-the-art results for automated game-playing in many board games. The training and search algorithms are not game-specific, but every individual game that these approaches are applied to still requires domain knowledge for the implementation of the game’s rules, and constructing the neural network’s architecture – in particular the shapes of its input and output tensors. Ludii is a general game system that already contains over 1,000 different games, which can rapidly grow thanks to its powerful and user-friendly game description language. Polygames is a framework with training and search algorithms, which has already produced superhuman players for several board games. This paper describes the implementation of a bridge between Ludii and Polygames, which enables Polygames to train and evaluate models for games that are implemented and run through Ludii. We do not require any game-specific domain knowledge anymore, and instead leverage our domain knowledge of the Ludii system and its abstract state and move representations to write functions that can automatically determine the appropriate shapes for input and output tensors for any game implemented in Ludii. We describe experimental results for short training runs in a wide variety of different board games, and discuss several open problems and avenues for future research.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Editorial: Rankings and ratings Automated videogame mechanics generation with XVGDL Editorial: Jan Krabbenbos, Videogames, CG 2022 and the 2022 WCCC The 2022 World Computer Chess Championships The SSDF Chess Engine Rating List, 2020-12
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1