Physics-Based Novel Task Generation Through Disrupting and Constructing Causal Interactions

IF 1.7 4区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Chathura Gamage;Matthew Stephenson;Jochen Renz
{"title":"Physics-Based Novel Task Generation Through Disrupting and Constructing Causal Interactions","authors":"Chathura Gamage;Matthew Stephenson;Jochen Renz","doi":"10.1109/TG.2024.3385569","DOIUrl":null,"url":null,"abstract":"In response to the growing demand for AI systems that can operate the physical world, there has been an increasing interest in enhancing their physical reasoning capabilities. Equally crucial is the ability to handle unseen novel situations, as such situations frequently arise in real-world environments. To facilitate the development of AI systems with those abilities, researchers have developed testbeds with specialized tasks to evaluate agents' adaptation to novelty in physical environments. In this article, we propose a method for generating physics-based tasks with incorporated novelties to assess agents' novelty adaptation capabilities. The tasks are defined as causal sequences of physical interactions between objects, and novelties are strategically introduced to disrupt existing causal relationships and construct new ones. This approach ensures that agents must adapt to the effects of novelties to perform those tasks, enabling confident measurement of their novelty adaptation capabilities using task performance. Moreover, our methodology eliminates the need for manual task creation, unlike existing novelty-centric testbeds. The proposed method is demonstrated and evaluated using 12 physical scenarios in the <italic>Angry Birds</i> domain. The evaluated metrics include generation time, physical stability, intended solvability, intended unsolvability, and accidental solvability of the tasks, and they yielded favourable results compared with the literature.","PeriodicalId":55977,"journal":{"name":"IEEE Transactions on Games","volume":"17 1","pages":"102-114"},"PeriodicalIF":1.7000,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Games","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10493164/","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

In response to the growing demand for AI systems that can operate the physical world, there has been an increasing interest in enhancing their physical reasoning capabilities. Equally crucial is the ability to handle unseen novel situations, as such situations frequently arise in real-world environments. To facilitate the development of AI systems with those abilities, researchers have developed testbeds with specialized tasks to evaluate agents' adaptation to novelty in physical environments. In this article, we propose a method for generating physics-based tasks with incorporated novelties to assess agents' novelty adaptation capabilities. The tasks are defined as causal sequences of physical interactions between objects, and novelties are strategically introduced to disrupt existing causal relationships and construct new ones. This approach ensures that agents must adapt to the effects of novelties to perform those tasks, enabling confident measurement of their novelty adaptation capabilities using task performance. Moreover, our methodology eliminates the need for manual task creation, unlike existing novelty-centric testbeds. The proposed method is demonstrated and evaluated using 12 physical scenarios in the Angry Birds domain. The evaluated metrics include generation time, physical stability, intended solvability, intended unsolvability, and accidental solvability of the tasks, and they yielded favourable results compared with the literature.
通过扰乱和构建因果互动生成基于物理学的新任务
为了应对对能够操作物理世界的人工智能系统日益增长的需求,人们对增强其物理推理能力的兴趣越来越大。同样重要的是处理未见过的新情况的能力,因为这种情况经常出现在现实环境中。为了促进具有这些能力的人工智能系统的发展,研究人员开发了具有专门任务的试验台,以评估智能体对物理环境中新事物的适应能力。在本文中,我们提出了一种方法来生成包含新颖性的基于物理的任务,以评估智能体的新颖性适应能力。任务被定义为对象之间物理相互作用的因果序列,并且战略性地引入新奇事物来破坏现有的因果关系并构建新的因果关系。这种方法确保代理必须适应新颖性的影响来执行这些任务,从而能够通过任务绩效自信地测量他们的新颖性适应能力。此外,我们的方法消除了手动创建任务的需要,这与现有的以新奇为中心的测试平台不同。该方法在愤怒的小鸟领域使用12个物理场景进行了演示和评估。评估的指标包括生成时间、物理稳定性、预期可解性、预期不可解性和任务的意外可解性,与文献相比,它们产生了有利的结果。
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
IEEE Transactions on Games
IEEE Transactions on Games Engineering-Electrical and Electronic Engineering
CiteScore
4.60
自引率
8.70%
发文量
87
×
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:481959085
Book学术官方微信