认知结构的内在动力:源于模式发现的求知欲。

IF 3 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Frontiers in Artificial Intelligence Pub Date : 2024-10-17 eCollection Date: 2024-01-01 DOI:10.3389/frai.2024.1397860
Kazuma Nagashima, Junya Morita, Yugo Takeuchi
{"title":"认知结构的内在动力:源于模式发现的求知欲。","authors":"Kazuma Nagashima, Junya Morita, Yugo Takeuchi","doi":"10.3389/frai.2024.1397860","DOIUrl":null,"url":null,"abstract":"<p><p>Studies on reinforcement learning have developed the representation of curiosity, which is a type of intrinsic motivation that leads to high performance in a certain type of tasks. However, these studies have not thoroughly examined the internal cognitive mechanisms leading to this performance. In contrast to this previous framework, we propose a mechanism of intrinsic motivation focused on pattern discovery from the perspective of human cognition. This study deals with intellectual curiosity as a type of intrinsic motivation, which finds novel compressible patterns in the data. We represented the process of continuation and boredom of tasks driven by intellectual curiosity using \"pattern matching,\" \"utility,\" and \"production compilation,\" which are general functions of the adaptive control of thought-rational (ACT-R) architecture. We implemented three ACT-R models with different levels of thinking to navigate multiple mazes of different sizes in simulations, manipulating the intensity of intellectual curiosity. The results indicate that intellectual curiosity negatively affects task completion rates in models with lower levels of thinking, while positively impacting models with higher levels of thinking. In addition, comparisons with a model developed by a conventional framework of reinforcement learning (intrinsic curiosity module: ICM) indicate the advantage of representing the agent's intention toward a goal in the proposed mechanism. In summary, the reported models, developed using functions linked to a general cognitive architecture, can contribute to our understanding of intrinsic motivation within the broader context of human innovation driven by pattern discovery.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":3.0000,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11525000/pdf/","citationCount":"0","resultStr":"{\"title\":\"Intrinsic motivation in cognitive architecture: intellectual curiosity originated from pattern discovery.\",\"authors\":\"Kazuma Nagashima, Junya Morita, Yugo Takeuchi\",\"doi\":\"10.3389/frai.2024.1397860\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Studies on reinforcement learning have developed the representation of curiosity, which is a type of intrinsic motivation that leads to high performance in a certain type of tasks. However, these studies have not thoroughly examined the internal cognitive mechanisms leading to this performance. In contrast to this previous framework, we propose a mechanism of intrinsic motivation focused on pattern discovery from the perspective of human cognition. This study deals with intellectual curiosity as a type of intrinsic motivation, which finds novel compressible patterns in the data. We represented the process of continuation and boredom of tasks driven by intellectual curiosity using \\\"pattern matching,\\\" \\\"utility,\\\" and \\\"production compilation,\\\" which are general functions of the adaptive control of thought-rational (ACT-R) architecture. We implemented three ACT-R models with different levels of thinking to navigate multiple mazes of different sizes in simulations, manipulating the intensity of intellectual curiosity. The results indicate that intellectual curiosity negatively affects task completion rates in models with lower levels of thinking, while positively impacting models with higher levels of thinking. In addition, comparisons with a model developed by a conventional framework of reinforcement learning (intrinsic curiosity module: ICM) indicate the advantage of representing the agent's intention toward a goal in the proposed mechanism. In summary, the reported models, developed using functions linked to a general cognitive architecture, can contribute to our understanding of intrinsic motivation within the broader context of human innovation driven by pattern discovery.</p>\",\"PeriodicalId\":33315,\"journal\":{\"name\":\"Frontiers in Artificial Intelligence\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.0000,\"publicationDate\":\"2024-10-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11525000/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers in Artificial Intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3389/frai.2024.1397860\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3389/frai.2024.1397860","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

关于强化学习的研究已经发展了好奇心的表征,好奇心是一种内在动机,会导致在某类任务中取得优异成绩。然而,这些研究并没有深入研究导致这种表现的内在认知机制。与以往的研究框架不同,我们从人类认知的角度出发,提出了一种以模式发现为核心的内在动机机制。本研究将求知欲作为内在动机的一种,它能从数据中发现新颖的可压缩模式。我们用 "模式匹配"、"效用 "和 "生产编译 "来表示求知欲驱动的任务的持续和厌倦过程,这些都是思维理性自适应控制(ACT-R)架构的一般功能。我们在模拟中实施了三种具有不同思维水平的 ACT-R 模型,通过操纵求知欲的强度来浏览多个不同大小的迷宫。结果表明,在思维水平较低的模型中,求知欲会对任务完成率产生负面影响,而在思维水平较高的模型中,求知欲则会对任务完成率产生正面影响。此外,与传统强化学习框架(内在好奇心模块:ICM)所开发的模型进行的比较表明,在所提出的机制中代表代理对目标的意图具有优势。总之,所报告的模型是利用与一般认知架构相关联的功能开发的,有助于我们在由模式发现驱动的人类创新的大背景下理解内在动机。
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
Intrinsic motivation in cognitive architecture: intellectual curiosity originated from pattern discovery.

Studies on reinforcement learning have developed the representation of curiosity, which is a type of intrinsic motivation that leads to high performance in a certain type of tasks. However, these studies have not thoroughly examined the internal cognitive mechanisms leading to this performance. In contrast to this previous framework, we propose a mechanism of intrinsic motivation focused on pattern discovery from the perspective of human cognition. This study deals with intellectual curiosity as a type of intrinsic motivation, which finds novel compressible patterns in the data. We represented the process of continuation and boredom of tasks driven by intellectual curiosity using "pattern matching," "utility," and "production compilation," which are general functions of the adaptive control of thought-rational (ACT-R) architecture. We implemented three ACT-R models with different levels of thinking to navigate multiple mazes of different sizes in simulations, manipulating the intensity of intellectual curiosity. The results indicate that intellectual curiosity negatively affects task completion rates in models with lower levels of thinking, while positively impacting models with higher levels of thinking. In addition, comparisons with a model developed by a conventional framework of reinforcement learning (intrinsic curiosity module: ICM) indicate the advantage of representing the agent's intention toward a goal in the proposed mechanism. In summary, the reported models, developed using functions linked to a general cognitive architecture, can contribute to our understanding of intrinsic motivation within the broader context of human innovation driven by pattern discovery.

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
CiteScore
6.10
自引率
2.50%
发文量
272
审稿时长
13 weeks
期刊最新文献
Impact of hypertension on coronary artery plaques and FFR-CT in type 2 diabetes mellitus patients: evaluation utilizing artificial intelligence processed coronary computed tomography angiography. Using large language models to support pre-service teachers mathematical reasoning-an exploratory study on ChatGPT as an instrument for creating mathematical proofs in geometry. Prediction of unobserved bifurcation by unsupervised extraction of slowly time-varying system parameter dynamics from time series using reservoir computing. Enzyme catalytic efficiency prediction: employing convolutional neural networks and XGBoost. Heuristic machine learning approaches for identifying phishing threats across web and email platforms.
×
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