Avoiding Negative Side Effects due to Incomplete Knowledge of AI Systems

Author:

Saisubramanian Sandhya1,Zilberstein Shlomo2,Kamar Ece3

Affiliation:

1. Oregon State University

2. University of Massachusetts

3. Microsoft Research

Abstract

AbstractAutonomous agents acting in the real‐world often operate based on models that ignore certain aspects of the environment. The incompleteness of any given model – handcrafted or machine acquired – is inevitable due to practical limitations of any modeling technique for complex real‐world settings. Due to the limited fidelity of its model, an agent's actions may have unexpected, undesirable consequences during execution. Learning to recognize and avoid such negative side effects (NSEs) of an agent's actions is critical to improve the safety and reliability of autonomous systems. Mitigating NSEs is an emerging research topic that is attracting increased attention due to the rapid growth in the deployment of AI systems and their broad societal impacts. This article provides a comprehensive overview of different forms of NSEs and the recent research efforts to address them. We identify key characteristics of NSEs, highlight the challenges in avoiding NSEs, and discuss recently developed approaches, contrasting their benefits and limitations. The article concludes with a discussion of open questions and suggestions for future research directions.

Funder

Semiconductor Research Corporation

Publisher

Wiley

Subject

Artificial Intelligence

Reference50 articles.

1. Barocas S. K.Crawford A.Shapiro&H.Wallach2017. “The problem with bias: Allocative versus representational harms in machine learning.” In Proceedings of the 9th Annual Conference of the Special Interest Group for Computing Information and Society. October 2017. Philadelphia Pennsylvania USA.

2. Artificial intelligence framework for simulating clinical decision-making: A Markov decision process approach

3. Wild patterns: Ten years after the rise of adversarial machine learning

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Exploratory machine learning with unknown unknowns;Artificial Intelligence;2024-02

2. AI safety of film capacitors;IET Nanodielectrics;2023-11-16

3. Avoiding Negative Side Effects of Autonomous Systems in the Open World;Journal of Artificial Intelligence Research;2022-05-10

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3