AIXI Responses to Newcomblike Problems

viXra Pub Date : 2020-06-01 DOI:10.31219/osf.io/kjrx9
Davide Zagami
{"title":"AIXI Responses to Newcomblike Problems","authors":"Davide Zagami","doi":"10.31219/osf.io/kjrx9","DOIUrl":null,"url":null,"abstract":"We provide a rigorous analysis of AIXI's behaviour under repeated Newcomblike settings. In this context, a Newcomblike problem is a setting where an agent is tied against an environment that contains a perfect predictor, whose predictions are used to determine the environmet's outputs. Since AIXI lacks good convergence properties, we chose to focus the analysis on determining whether an environment appears computable to AIXI, that is, if it maps actions to observations in a way that a computable program can achieve. It is in this sense that, it turns out, AIXI can learn to one-box in *repeated* Opaque Newcomb, and to smoke in *repeated* Smoking Lesion, but may fail all other Newcomblike problems, because we found no way to reduce them in a computable form. However, we still suspect that AIXI can succeed in the repeated settings.","PeriodicalId":23650,"journal":{"name":"viXra","volume":"19 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"viXra","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.31219/osf.io/kjrx9","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

We provide a rigorous analysis of AIXI's behaviour under repeated Newcomblike settings. In this context, a Newcomblike problem is a setting where an agent is tied against an environment that contains a perfect predictor, whose predictions are used to determine the environmet's outputs. Since AIXI lacks good convergence properties, we chose to focus the analysis on determining whether an environment appears computable to AIXI, that is, if it maps actions to observations in a way that a computable program can achieve. It is in this sense that, it turns out, AIXI can learn to one-box in *repeated* Opaque Newcomb, and to smoke in *repeated* Smoking Lesion, but may fail all other Newcomblike problems, because we found no way to reduce them in a computable form. However, we still suspect that AIXI can succeed in the repeated settings.
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
AIXI对newcomb类问题的回应
我们对AIXI在重复newcomb设置下的行为进行了严格的分析。在这个上下文中,类似newcomb的问题是这样一种设置,其中代理与包含完美预测器的环境相关联,该预测器的预测用于确定环境的输出。由于AIXI缺乏良好的收敛特性,我们选择将分析重点放在确定环境是否对AIXI来说是可计算的,也就是说,如果它以可计算程序可以实现的方式将操作映射到观察。正是在这个意义上,事实证明,AIXI可以学会在*重复*不透明的Newcomb中装一个盒子,并在*重复*吸烟病变中吸烟,但可能无法解决所有其他类似Newcomb的问题,因为我们没有找到将它们简化为可计算形式的方法。但是,我们仍然怀疑AIXI能够在重复设置中成功。
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 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Relation of Accelerations in Two Inertial Frames in Special Relativity Theory Ultra-High Sensitivity MEMS Pressure Sensor Utilizing Bipolar Junction Transistor for -1…+1 kPa Investigation of High Sensitivity Piezoresistive Pressure Sensors for -0.5…+0.5 kPa Modeling of sensitive element for pressure sensor based on bipolar piezotransistor Four Spacetime Dimensions from Multifractal Geometry
×
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