一个独立于领域的系统,用于描述和规划新情况

IF 4.6 2区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Bryan Loyall , Avi Pfeffer , James Niehaus , Michael Harradon , Paola Rizzo , Alex Gee , Joe Campolongo , Tyler Mayer , John Steigerwald
{"title":"一个独立于领域的系统,用于描述和规划新情况","authors":"Bryan Loyall ,&nbsp;Avi Pfeffer ,&nbsp;James Niehaus ,&nbsp;Michael Harradon ,&nbsp;Paola Rizzo ,&nbsp;Alex Gee ,&nbsp;Joe Campolongo ,&nbsp;Tyler Mayer ,&nbsp;John Steigerwald","doi":"10.1016/j.artint.2025.104336","DOIUrl":null,"url":null,"abstract":"<div><div>AI systems operating in open-world environments must be able to adapt to impactful changes in the world, immediately when they occur, and be able to do this across the many types of changes that can occur. We are seeking to create methods to extend traditional AI systems so that they can (1) immediately recognize changes in how the world works that are impactful to task accomplishment; (2) rapidly characterize the nature of the change using the limited observations that are available when the change is first detected; (3) adapt to the change as well as feasible to accomplish the system's tasks given the available observations; and (4) continue to improve the characterization and adaptation as additional observations are available. In this paper, we describe Coltrane, a domain-independent system for characterizing and planning in novel situations that uses only natural domain descriptions to generate its novelty-handling behavior, without any domain-specific anticipation of the novelty. Coltrane's characterization method is based on probabilistic program synthesis of perturbations to programs expressed in a traditional programming language describing domain transition models. Its planning method is based on incorporating novel domain models in an MCTS search algorithm and on automatically adapting the heuristics used. Both a formal external evaluation and our own demonstrations show that Coltrane is capable of accurately characterizing interesting forms of novelty and of adapting its behavior to restore its performance to pre-novelty levels and even beyond.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"345 ","pages":"Article 104336"},"PeriodicalIF":4.6000,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Coltrane: A domain-independent system for characterizing and planning in novel situations\",\"authors\":\"Bryan Loyall ,&nbsp;Avi Pfeffer ,&nbsp;James Niehaus ,&nbsp;Michael Harradon ,&nbsp;Paola Rizzo ,&nbsp;Alex Gee ,&nbsp;Joe Campolongo ,&nbsp;Tyler Mayer ,&nbsp;John Steigerwald\",\"doi\":\"10.1016/j.artint.2025.104336\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>AI systems operating in open-world environments must be able to adapt to impactful changes in the world, immediately when they occur, and be able to do this across the many types of changes that can occur. We are seeking to create methods to extend traditional AI systems so that they can (1) immediately recognize changes in how the world works that are impactful to task accomplishment; (2) rapidly characterize the nature of the change using the limited observations that are available when the change is first detected; (3) adapt to the change as well as feasible to accomplish the system's tasks given the available observations; and (4) continue to improve the characterization and adaptation as additional observations are available. In this paper, we describe Coltrane, a domain-independent system for characterizing and planning in novel situations that uses only natural domain descriptions to generate its novelty-handling behavior, without any domain-specific anticipation of the novelty. Coltrane's characterization method is based on probabilistic program synthesis of perturbations to programs expressed in a traditional programming language describing domain transition models. Its planning method is based on incorporating novel domain models in an MCTS search algorithm and on automatically adapting the heuristics used. Both a formal external evaluation and our own demonstrations show that Coltrane is capable of accurately characterizing interesting forms of novelty and of adapting its behavior to restore its performance to pre-novelty levels and even beyond.</div></div>\",\"PeriodicalId\":8434,\"journal\":{\"name\":\"Artificial Intelligence\",\"volume\":\"345 \",\"pages\":\"Article 104336\"},\"PeriodicalIF\":4.6000,\"publicationDate\":\"2025-04-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Artificial Intelligence\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0004370225000554\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Artificial Intelligence","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0004370225000554","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

在开放世界环境中运行的人工智能系统必须能够适应世界中有影响力的变化,当它们发生时立即适应,并且能够跨越可能发生的多种变化。我们正在寻求创造方法来扩展传统的人工智能系统,以便它们能够(1)立即识别对任务完成有影响的世界运作方式的变化;(2)利用第一次探测到变化时可获得的有限观测资料,迅速表征变化的性质;(3)在给定观测值的情况下,适应变化并可行地完成系统的任务;(4)随着获得更多观测数据,继续改进特征和适应。在本文中,我们描述了Coltrane,一个独立于领域的系统,用于描述和规划新颖的情况,它只使用自然的领域描述来生成其新颖性处理行为,没有任何特定于领域的新颖性预期。Coltrane的表征方法是基于对用传统编程语言描述域转移模型的程序表示的扰动的概率程序综合。它的规划方法是基于在MCTS搜索算法中加入新的领域模型并自动适应所使用的启发式算法。正式的外部评估和我们自己的演示都表明,Coltrane能够准确地描述新奇的有趣形式,并调整其行为以恢复其表现到新奇之前的水平,甚至更高。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Coltrane: A domain-independent system for characterizing and planning in novel situations
AI systems operating in open-world environments must be able to adapt to impactful changes in the world, immediately when they occur, and be able to do this across the many types of changes that can occur. We are seeking to create methods to extend traditional AI systems so that they can (1) immediately recognize changes in how the world works that are impactful to task accomplishment; (2) rapidly characterize the nature of the change using the limited observations that are available when the change is first detected; (3) adapt to the change as well as feasible to accomplish the system's tasks given the available observations; and (4) continue to improve the characterization and adaptation as additional observations are available. In this paper, we describe Coltrane, a domain-independent system for characterizing and planning in novel situations that uses only natural domain descriptions to generate its novelty-handling behavior, without any domain-specific anticipation of the novelty. Coltrane's characterization method is based on probabilistic program synthesis of perturbations to programs expressed in a traditional programming language describing domain transition models. Its planning method is based on incorporating novel domain models in an MCTS search algorithm and on automatically adapting the heuristics used. Both a formal external evaluation and our own demonstrations show that Coltrane is capable of accurately characterizing interesting forms of novelty and of adapting its behavior to restore its performance to pre-novelty levels and even beyond.
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
Artificial Intelligence
Artificial Intelligence 工程技术-计算机:人工智能
CiteScore
11.20
自引率
1.40%
发文量
118
审稿时长
8 months
期刊介绍: The Journal of Artificial Intelligence (AIJ) welcomes papers covering a broad spectrum of AI topics, including cognition, automated reasoning, computer vision, machine learning, and more. Papers should demonstrate advancements in AI and propose innovative approaches to AI problems. Additionally, the journal accepts papers describing AI applications, focusing on how new methods enhance performance rather than reiterating conventional approaches. In addition to regular papers, AIJ also accepts Research Notes, Research Field Reviews, Position Papers, Book Reviews, and summary papers on AI challenges and competitions.
×
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