从游戏注解中学习

Christian Wirth, Johannes Furnkranz
{"title":"从游戏注解中学习","authors":"Christian Wirth, Johannes Furnkranz","doi":"10.1109/TCIAIG.2014.2332442","DOIUrl":null,"url":null,"abstract":"Most of the research in the area of evaluation function learning is focused on self-play. However in many domains, like Chess, expert feedback is amply available in the form of annotated games. This feedback usually comes in the form of qualitative information because human annotators find it hard to determine precise utility values for game states. The goal of this work is to investigate inasmuch it is possible to leverage this qualitative feedback for learning an evaluation function for the game. To this end, we show how the game annotations can be translated into preference statements over moves and game states, which in turn can be used for learning a utility function that respects these preference constraints. We evaluate the resulting function by creating multiple heuristics based upon different sized subsets of the training data and compare them in a tournament scenario. The results showed that learning from game annotations is possible, but, on the other hand, our learned functions did not quite reach the performance of the original, manually tuned function of the Chess program. The reason for this failure seems to lie in the fact that human annotators only annotate “interesting” positions, so that it is hard to learn basic information, such as material advantage from game annotations alone.","PeriodicalId":49192,"journal":{"name":"IEEE Transactions on Computational Intelligence and AI in Games","volume":"7 1","pages":"304-316"},"PeriodicalIF":0.0000,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TCIAIG.2014.2332442","citationCount":"21","resultStr":"{\"title\":\"On Learning From Game Annotations\",\"authors\":\"Christian Wirth, Johannes Furnkranz\",\"doi\":\"10.1109/TCIAIG.2014.2332442\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Most of the research in the area of evaluation function learning is focused on self-play. However in many domains, like Chess, expert feedback is amply available in the form of annotated games. This feedback usually comes in the form of qualitative information because human annotators find it hard to determine precise utility values for game states. The goal of this work is to investigate inasmuch it is possible to leverage this qualitative feedback for learning an evaluation function for the game. To this end, we show how the game annotations can be translated into preference statements over moves and game states, which in turn can be used for learning a utility function that respects these preference constraints. We evaluate the resulting function by creating multiple heuristics based upon different sized subsets of the training data and compare them in a tournament scenario. The results showed that learning from game annotations is possible, but, on the other hand, our learned functions did not quite reach the performance of the original, manually tuned function of the Chess program. The reason for this failure seems to lie in the fact that human annotators only annotate “interesting” positions, so that it is hard to learn basic information, such as material advantage from game annotations alone.\",\"PeriodicalId\":49192,\"journal\":{\"name\":\"IEEE Transactions on Computational Intelligence and AI in Games\",\"volume\":\"7 1\",\"pages\":\"304-316\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1109/TCIAIG.2014.2332442\",\"citationCount\":\"21\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Computational Intelligence and AI in Games\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/TCIAIG.2014.2332442\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"Computer Science\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Computational Intelligence and AI in Games","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TCIAIG.2014.2332442","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Computer Science","Score":null,"Total":0}
引用次数: 21

摘要

评价函数学习领域的研究大多集中在自我游戏方面。然而在许多领域,如象棋,专家反馈以注释游戏的形式存在。这种反馈通常以定性信息的形式出现,因为人类注释者很难确定游戏状态的精确效用值。这项工作的目标是调查,因为有可能利用这种定性反馈来学习游戏的评估功能。为此,我们展示了如何将游戏注释转换为关于移动和游戏状态的偏好陈述,这反过来又可以用于学习尊重这些偏好约束的效用函数。我们通过基于不同大小的训练数据子集创建多个启发式方法来评估结果函数,并在锦标赛场景中对它们进行比较。结果表明,从游戏注释中学习是可能的,但是,另一方面,我们学习的函数并没有完全达到原始的、手动调整的国际象棋程序函数的性能。这种失败的原因似乎在于人类注释者只注释“有趣”的位置,因此很难从游戏注释中学习到基本信息,例如材料优势。
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
On Learning From Game Annotations
Most of the research in the area of evaluation function learning is focused on self-play. However in many domains, like Chess, expert feedback is amply available in the form of annotated games. This feedback usually comes in the form of qualitative information because human annotators find it hard to determine precise utility values for game states. The goal of this work is to investigate inasmuch it is possible to leverage this qualitative feedback for learning an evaluation function for the game. To this end, we show how the game annotations can be translated into preference statements over moves and game states, which in turn can be used for learning a utility function that respects these preference constraints. We evaluate the resulting function by creating multiple heuristics based upon different sized subsets of the training data and compare them in a tournament scenario. The results showed that learning from game annotations is possible, but, on the other hand, our learned functions did not quite reach the performance of the original, manually tuned function of the Chess program. The reason for this failure seems to lie in the fact that human annotators only annotate “interesting” positions, so that it is hard to learn basic information, such as material advantage from game annotations alone.
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
IEEE Transactions on Computational Intelligence and AI in Games
IEEE Transactions on Computational Intelligence and AI in Games COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-COMPUTER SCIENCE, SOFTWARE ENGINEERING
CiteScore
4.60
自引率
0.00%
发文量
0
审稿时长
>12 weeks
期刊介绍: Cessation. The IEEE Transactions on Computational Intelligence and AI in Games (T-CIAIG) publishes archival journal quality original papers in computational intelligence and related areas in artificial intelligence applied to games, including but not limited to videogames, mathematical games, human–computer interactions in games, and games involving physical objects. Emphasis is placed on the use of these methods to improve performance in and understanding of the dynamics of games, as well as gaining insight into the properties of the methods as applied to games. It also includes using games as a platform for building intelligent embedded agents for the real world. Papers connecting games to all areas of computational intelligence and traditional AI are considered.
期刊最新文献
A User Trust System for Online Games—Part II: A Subjective Logic Approach for Trust Inference Accelerating Board Games Through Hardware/Software Codesign Creating AI Characters for Fighting Games Using Genetic Programming Multiagent Path Finding With Persistence Conflicts Changing Resources Available to Game Playing Agents: Another Relevant Design Factor in Agent Experiments
×
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