Evolving a Mario agent using cuckoo search and softmax heuristics

Erek R. Speed
{"title":"Evolving a Mario agent using cuckoo search and softmax heuristics","authors":"Erek R. Speed","doi":"10.1109/ICEGIC.2010.5716893","DOIUrl":null,"url":null,"abstract":"This paper presents a method for evolving an agent which can successfully play a level of Super Mario Brothers as implemented on the MarioAI Benchmark. The Mario search space is extremely large, making finding reasonable solutions intractable for ordinary agents. The recently introduced evolutionary algorithm, cuckoo search is especially well suited toward searching such large spaces when it employs the use of Le´vy flights. Unfortunately, these Le´vy flights cannot be applied to non numerical problems such as Mario. We present a modification of the algorithm which uses the Le´vy distribution to effect appropriate change in a much wider set of problems, including Mario. To further optimize the search of Mario's problem space, a softmax heuristic is presented to focus on areas with likely solutions.","PeriodicalId":229345,"journal":{"name":"2010 2nd International IEEE Consumer Electronics Society's Games Innovations Conference","volume":"28 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"27","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 2nd International IEEE Consumer Electronics Society's Games Innovations Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICEGIC.2010.5716893","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 27

Abstract

This paper presents a method for evolving an agent which can successfully play a level of Super Mario Brothers as implemented on the MarioAI Benchmark. The Mario search space is extremely large, making finding reasonable solutions intractable for ordinary agents. The recently introduced evolutionary algorithm, cuckoo search is especially well suited toward searching such large spaces when it employs the use of Le´vy flights. Unfortunately, these Le´vy flights cannot be applied to non numerical problems such as Mario. We present a modification of the algorithm which uses the Le´vy distribution to effect appropriate change in a much wider set of problems, including Mario. To further optimize the search of Mario's problem space, a softmax heuristic is presented to focus on areas with likely solutions.
使用布谷鸟搜索和softmax启发式方法进化马里奥代理
本文提出了一种进化智能体的方法,该方法可以在MarioAI基准测试上成功完成《超级马里奥兄弟》的关卡。马里奥的搜索空间非常大,使得普通代理难以找到合理的解决方案。最近引入的进化算法,布谷鸟搜索特别适合于搜索如此大的空间,当它使用勒维飞行时。不幸的是,这些勒维飞行不能应用于像马里奥这样的非数值问题。我们提出了对该算法的修改,该算法使用Le´vy分布来对更广泛的问题(包括Mario)进行适当的更改。为了进一步优化马里奥问题空间的搜索,提出了一个softmax启发式算法来关注可能解的区域。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信