Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society最新文献_第8页

Human-AI Learning Performance in Multi-Armed Bandits 人工智能在多武装土匪中的学习表现

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-12-21 DOI: 10.1145/3306618.3314245

Ravi Pandya, Sandy H. Huang, Dylan Hadfield-Menell, A. Dragan

{"title":"Human-AI Learning Performance in Multi-Armed Bandits","authors":"Ravi Pandya, Sandy H. Huang, Dylan Hadfield-Menell, A. Dragan","doi":"10.1145/3306618.3314245","DOIUrl":"https://doi.org/10.1145/3306618.3314245","url":null,"abstract":"People frequently face challenging decision-making problems in which outcomes are uncertain or unknown. Artificial intelligence (AI) algorithms exist that can outperform humans at learning such tasks. Thus, there is an opportunity for AI agents to assist people in learning these tasks more effectively. In this work, we use a multi-armed bandit as a controlled setting in which to explore this direction. We pair humans with a selection of agents and observe how well each human-agent team performs. We find that team performance can beat both human and agent performance in isolation. Interestingly, we also find that an agent's performance in isolation does not necessarily correlate with the human-agent team's performance. A drop in agent performance can lead to a disproportionately large drop in team performance, or in some settings can even improve team performance. Pairing a human with an agent that performs slightly better than them can make them perform much better, while pairing them with an agent that performs the same can make them them perform much worse. Further, our results suggest that people have different exploration strategies and might perform better with agents that match their strategy. Overall, optimizing human-agent team performance requires going beyond optimizing agent performance, to understanding how the agent's suggestions will influence human decision-making.","PeriodicalId":418125,"journal":{"name":"Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society","volume":"32 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120980799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

What are the Biases in My Word Embedding? 我的词嵌入有什么偏差?

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-12-20 DOI: 10.1145/3306618.3314270

Nathaniel Swinger, Maria De-Arteaga, IV NeilThomasHeffernan, Mark D. M. Leiserson, A. Kalai

{"title":"What are the Biases in My Word Embedding?","authors":"Nathaniel Swinger, Maria De-Arteaga, IV NeilThomasHeffernan, Mark D. M. Leiserson, A. Kalai","doi":"10.1145/3306618.3314270","DOIUrl":"https://doi.org/10.1145/3306618.3314270","url":null,"abstract":"This paper presents an algorithm for enumerating biases in word embeddings. The algorithm exposes a large number of offensive associations related to sensitive features such as race and gender on publicly available embeddings, including a supposedly \"debiased\" embedding. These biases are concerning in light of the widespread use of word embeddings. The associations are identified by geometric patterns in word embeddings that run parallel between people's names and common lower-case tokens. The algorithm is highly unsupervised: it does not even require the sensitive features to be pre-specified. This is desirable because: (a) many forms of discrimination?such as racial discrimination-are linked to social constructs that may vary depending on the context, rather than to categories with fixed definitions; and (b) it makes it easier to identify biases against intersectional groups, which depend on combinations of sensitive features. The inputs to our algorithm are a list of target tokens, e.g. names, and a word embedding. It outputs a number of Word Embedding Association Tests (WEATs) that capture various biases present in the data. We illustrate the utility of our approach on publicly available word embeddings and lists of names, and evaluate its output using crowdsourcing. We also show how removing names may not remove potential proxy bias.","PeriodicalId":418125,"journal":{"name":"Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society","volume":"1998 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128229910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 89

Using Deceased-Donor Kidneys to Initiate Chains of Living Donor Kidney Paired Donations: Algorithm and Experimentation 利用已故供者肾脏启动活体供者肾脏配对捐献链:算法与实验

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-12-17 DOI: 10.1145/3306618.3314276

Cristina Cornelio, L. Furian, Antonio Nicolò, Francesca Rossi

引用次数: 3

Building Jiminy Cricket: An Architecture for Moral Agreements Among Stakeholders 构建小蟋蟀:利益相关者之间道德协议的架构

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-12-11 DOI: 10.1145/3306618.3314257

B. Liao, M. Slavkovik, Leendert van der Torre

引用次数: 22

Toward the Engineering of Virtuous Machines 迈向良性机器的工程

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-12-07 DOI: 10.1145/3306618.3314256

Naveen Sundar Govindarajulu, S. Bringsjord, Rikhiya Ghosh, Vasanth Sarathy

引用次数: 25

Reinforcement Learning and Inverse Reinforcement Learning with System 1 and System 2 系统1和系统2的强化学习和逆强化学习

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-11-19 DOI: 10.1145/3306618.3314259

A. Peysakhovich

{"title":"Reinforcement Learning and Inverse Reinforcement Learning with System 1 and System 2","authors":"A. Peysakhovich","doi":"10.1145/3306618.3314259","DOIUrl":"https://doi.org/10.1145/3306618.3314259","url":null,"abstract":"Inferring a person's goal from their behavior is an important problem in applications of AI (e.g. automated assistants, recommender systems). The workhorse model for this task is the rational actor model - this amounts to assuming that people have stable reward functions, discount the future exponentially, and construct optimal plans. Under the rational actor assumption techniques such as inverse reinforcement learning (IRL) can be used to infer a person's goals from their actions. A competing model is the dual-system model. Here decisions are the result of an interplay between a fast, automatic, heuristic-based system 1 and a slower, deliberate, calculating system 2. We generalize the dual system framework to the case of Markov decision problems and show how to compute optimal plans for dual-system agents. We show that dual-system agents exhibit behaviors that are incompatible with rational actor assumption. We show that naive applications of rational-actor IRL to the behavior of dual-system agents can generate wrong inference about the agents' goals and suggest interventions that actually reduce the agent's overall utility. Finally, we adapt a simple IRL algorithm to correctly infer the goals of dual system decision-makers. This allows us to make interventions that help, rather than hinder, the dual-system agent's ability to reach their true goals.","PeriodicalId":418125,"journal":{"name":"Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129404868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

TrolleyMod v1.0: An Open-Source Simulation and Data-Collection Platform for Ethical Decision Making in Autonomous Vehicles TrolleyMod v1.0:面向自动驾驶车辆伦理决策的开源仿真与数据采集平台

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-11-14 DOI: 10.1145/3306618.3314239

Vahid Behzadan, J. Minton, Arslan Munir

引用次数: 1

TED: Teaching AI to Explain its Decisions TED:教人工智能解释它的决定

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-11-12 DOI: 10.1145/3306618.3314273

N. Codella, M. Hind, K. Ramamurthy, Murray Campbell, Amit Dhurandhar, Kush R. Varshney, Dennis Wei, A. Mojsilovic

引用次数: 90

How Do Fairness Definitions Fare?: Examining Public Attitudes Towards Algorithmic Definitions of Fairness 公平的定义如何?调查公众对公平的算法定义的态度

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-11-08 DOI: 10.1145/3306618.3314248

N. Saxena, Karen Huang, Evan DeFilippis, Goran Radanovic, D. Parkes, Y. Liu

引用次数: 136

Legible Normativity for AI Alignment: The Value of Silly Rules AI对齐的易读规范性:愚蠢规则的价值

Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society Pub Date : 2018-11-03 DOI: 10.1145/3306618.3314258

Dylan Hadfield-Menell, McKane Andrus, Gillian K. Hadfield

引用次数: 13