AI for Explaining Decisions in Multi-Agent Environments

Sarit Kraus; Amos Azaria; Jelena Fiosina; Maike Greve; Noam Hazon; Lutz Kolbe; Tim Benjamin Lembcke; Jörg P. Müller; Sören Schleibaum; Mark Vollrath

doi:10.1609/aaai.v34i09.7077

AI for Explaining Decisions in Multi-Agent Environments

Sarit Kraus^*, Amos Azaria, Jelena Fiosina, Maike Greve, Noam Hazon, Lutz Kolbe, Tim Benjamin Lembcke, Jörg P. Müller, Sören Schleibaum, Mark Vollrath

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Explanation is necessary for humans to understand and accept decisions made by an AI system when the system's goal is known. It is even more important when the AI system makes decisions in multi-agent environments where the human does not know the systems' goals since they may depend on other agents' preferences. In such situations, explanations should aim to increase user satisfaction, taking into account the system's decision, the user's and the other agents' preferences, the environment settings and properties such as fairness, envy and privacy. Generating explanations that will increase user satisfaction is very challenging; to this end, we propose a new research direction: Explainable decisions in Multi-Agent Environments (xMASE). We then review the state of the art and discuss research directions towards efficient methodologies and algorithms for generating explanations that will increase users' satisfaction from AI systems' decisions in multi-agent environments.

Original language	English
Title of host publication	AAAI-20 / IAAI-20 / EAAI-20 Proceedings
Number of pages	5
Place of Publication	Palo Alto, CA
Publisher	AAAI Press
Publication date	2020
Pages	13534-13538
ISBN (Electronic)	9781577358350
DOIs	https://doi.org/10.1609/aaai.v34i09.7077
Publication status	Published - 2020
Externally published	Yes
Event	34th AAAI Conference on Artificial Intelligence, AAAI 2020 - New York, United States Duration: 7 Feb 2020 → 12 Feb 2020 Conference number: 34 https://aaai.org/conference/aaai/aaai-20/

Conference

Conference	34th AAAI Conference on Artificial Intelligence, AAAI 2020
Number	34
Country/Territory	United States
City	New York
Period	07/02/2020 → 12/02/2020
Sponsor	Association for the Advancement of Artificial Intelligence
Internet address	https://aaai.org/conference/aaai/aaai-20/

Series	EAAI-20 / AAAI Special Programs
Number	9
Volume	34
ISSN	2159-5399

Access to Document

10.1609/aaai.v34i09.7077Licence: Unspecified

Handle.net

Persistent link

Cite this

@inproceedings{6eabd6e2872445cfb162512b619ad199,

title = "AI for Explaining Decisions in Multi-Agent Environments",

abstract = "Explanation is necessary for humans to understand and accept decisions made by an AI system when the system's goal is known. It is even more important when the AI system makes decisions in multi-agent environments where the human does not know the systems' goals since they may depend on other agents' preferences. In such situations, explanations should aim to increase user satisfaction, taking into account the system's decision, the user's and the other agents' preferences, the environment settings and properties such as fairness, envy and privacy. Generating explanations that will increase user satisfaction is very challenging; to this end, we propose a new research direction: Explainable decisions in Multi-Agent Environments (xMASE). We then review the state of the art and discuss research directions towards efficient methodologies and algorithms for generating explanations that will increase users' satisfaction from AI systems' decisions in multi-agent environments.",

author = "Sarit Kraus and Amos Azaria and Jelena Fiosina and Maike Greve and Noam Hazon and Lutz Kolbe and Lembcke, {Tim Benjamin} and M{\"u}ller, {J{\"o}rg P.} and S{\"o}ren Schleibaum and Mark Vollrath",

year = "2020",

doi = "10.1609/aaai.v34i09.7077",

language = "English",

series = "EAAI-20 / AAAI Special Programs",

publisher = "AAAI Press",

number = "9",

pages = "13534--13538",

booktitle = "AAAI-20 / IAAI-20 / EAAI-20 Proceedings",

address = "United States",

note = "34th AAAI Conference on Artificial Intelligence, AAAI 2020 ; Conference date: 07-02-2020 Through 12-02-2020",

url = "https://aaai.org/conference/aaai/aaai-20/",

}

Kraus, S, Azaria, A, Fiosina, J, Greve, M, Hazon, N, Kolbe, L, Lembcke, TB, Müller, JP, Schleibaum, S & Vollrath, M 2020, AI for Explaining Decisions in Multi-Agent Environments. in AAAI-20 / IAAI-20 / EAAI-20 Proceedings. AAAI Press, Palo Alto, CA, EAAI-20 / AAAI Special Programs, no. 9, vol. 34, pp. 13534-13538, 34th AAAI Conference on Artificial Intelligence, AAAI 2020, New York, New York, United States, 07/02/2020. https://doi.org/10.1609/aaai.v34i09.7077

TY - GEN

T1 - AI for Explaining Decisions in Multi-Agent Environments

AU - Kraus, Sarit

AU - Azaria, Amos

AU - Fiosina, Jelena

AU - Greve, Maike

AU - Hazon, Noam

AU - Kolbe, Lutz

AU - Lembcke, Tim Benjamin

AU - Müller, Jörg P.

AU - Schleibaum, Sören

AU - Vollrath, Mark

N1 - Conference code: 34

PY - 2020

Y1 - 2020

N2 - Explanation is necessary for humans to understand and accept decisions made by an AI system when the system's goal is known. It is even more important when the AI system makes decisions in multi-agent environments where the human does not know the systems' goals since they may depend on other agents' preferences. In such situations, explanations should aim to increase user satisfaction, taking into account the system's decision, the user's and the other agents' preferences, the environment settings and properties such as fairness, envy and privacy. Generating explanations that will increase user satisfaction is very challenging; to this end, we propose a new research direction: Explainable decisions in Multi-Agent Environments (xMASE). We then review the state of the art and discuss research directions towards efficient methodologies and algorithms for generating explanations that will increase users' satisfaction from AI systems' decisions in multi-agent environments.

AB - Explanation is necessary for humans to understand and accept decisions made by an AI system when the system's goal is known. It is even more important when the AI system makes decisions in multi-agent environments where the human does not know the systems' goals since they may depend on other agents' preferences. In such situations, explanations should aim to increase user satisfaction, taking into account the system's decision, the user's and the other agents' preferences, the environment settings and properties such as fairness, envy and privacy. Generating explanations that will increase user satisfaction is very challenging; to this end, we propose a new research direction: Explainable decisions in Multi-Agent Environments (xMASE). We then review the state of the art and discuss research directions towards efficient methodologies and algorithms for generating explanations that will increase users' satisfaction from AI systems' decisions in multi-agent environments.

U2 - 10.1609/aaai.v34i09.7077

DO - 10.1609/aaai.v34i09.7077

M3 - Article in proceedings

AN - SCOPUS:85097378516

T3 - EAAI-20 / AAAI Special Programs

SP - 13534

EP - 13538

BT - AAAI-20 / IAAI-20 / EAAI-20 Proceedings

PB - AAAI Press

CY - Palo Alto, CA

T2 - 34th AAAI Conference on Artificial Intelligence, AAAI 2020

Y2 - 7 February 2020 through 12 February 2020

ER -