Elessar: Ethics in Norm-Aware Agents

Nirav Ajmeri; P.K. Murukannaiah; Hui Guo; Munindar P. Singh

Elessar: Ethics in Norm-Aware Agents

Nirav Ajmeri, P.K. Murukannaiah, Hui Guo, Munindar P. Singh

Interactive Intelligence

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

28 Citations (Scopus)

366 Downloads (Pure)

Abstract

We address the problem of designing agents that navigate social norms by selecting ethically appropriate actions. We present Elessar, a framework in which agents aggregate value preferences of users and select ethically appropriate actions through multicriteria decision making in different social contexts. Via simulations, seeded with a survey of user values and attitudes, we find that Elessar agents act ethically and are effective than baseline agents, in terms of (1) exhibiting the Rawlsian property of fairness, and (2) yielding a satisfactory social experience to users. Our results are stable across agent societies of different sizes and connectedness.

Original language	English
Title of host publication	Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020
Editors	Bo An, Amal El Fallah Seghrouchni, Gita Sukthankar
Pages	16-24
Number of pages	9
ISBN (Electronic)	978-1-4503-7518-4
Publication status	Published - May 2020
Event	AAMAS 2020: The 19th International Conference on Autonomous Agents and Multi-Agent Systems - Auckland, New Zealand Duration: 9 May 2020 → 13 May 2020 Conference number: 19th https://aamas2020.conference.auckland.ac.nz

Publication series

Name	Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Volume	2020-May
ISSN (Print)	1548-8403
ISSN (Electronic)	1558-2914

Conference

Conference	AAMAS 2020
Country/Territory	New Zealand
City	Auckland
Period	9/05/20 → 13/05/20
Other	Virtual/online event due to COVID-19
Internet address	https://aamas2020.conference.auckland.ac.nz

Bibliographical note

Accepted Author Manuscript

Keywords

Ethics
Fairness
Preferences
Social norms
Values

Access to Document

Ajmeri-2020-AAMAS-ElessarAccepted author manuscript, 646 KB

Cite this

Ajmeri, N., Murukannaiah, P. K., Guo, H., & Singh, M. P. (2020). Elessar: Ethics in Norm-Aware Agents. In B. An, A. El Fallah Seghrouchni, & G. Sukthankar (Eds.), Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020 (pp. 16-24). (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS; Vol. 2020-May).

Ajmeri, Nirav ; Murukannaiah, P.K. ; Guo, Hui et al. / Elessar: Ethics in Norm-Aware Agents. Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020. editor / Bo An ; Amal El Fallah Seghrouchni ; Gita Sukthankar. 2020. pp. 16-24 (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS).

@inproceedings{86620c286b05444197b6107e581c4785,

title = "Elessar: Ethics in Norm-Aware Agents",

abstract = "We address the problem of designing agents that navigate social norms by selecting ethically appropriate actions. We present Elessar, a framework in which agents aggregate value preferences of users and select ethically appropriate actions through multicriteria decision making in different social contexts. Via simulations, seeded with a survey of user values and attitudes, we find that Elessar agents act ethically and are effective than baseline agents, in terms of (1) exhibiting the Rawlsian property of fairness, and (2) yielding a satisfactory social experience to users. Our results are stable across agent societies of different sizes and connectedness.",

keywords = "Ethics, Fairness, Preferences, Social norms, Values",

author = "Nirav Ajmeri and P.K. Murukannaiah and Hui Guo and Singh, {Munindar P.}",

note = "Accepted Author Manuscript; AAMAS 2020 : The 19th International Conference on Autonomous Agents and Multi-Agent Systems ; Conference date: 09-05-2020 Through 13-05-2020",

year = "2020",

month = may,

language = "English",

series = "Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS",

pages = "16--24",

editor = "Bo An and {El Fallah Seghrouchni}, {Amal } and Sukthankar, {Gita }",

booktitle = "Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020",

url = "https://aamas2020.conference.auckland.ac.nz",

}

Ajmeri, N, Murukannaiah, PK, Guo, H & Singh, MP 2020, Elessar: Ethics in Norm-Aware Agents. in B An, A El Fallah Seghrouchni & G Sukthankar (eds), Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020. Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, vol. 2020-May, pp. 16-24, AAMAS 2020, Auckland, New Zealand, 9/05/20.

Elessar: Ethics in Norm-Aware Agents. / Ajmeri, Nirav; Murukannaiah, P.K.; Guo, Hui et al.
Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020. ed. / Bo An; Amal El Fallah Seghrouchni; Gita Sukthankar. 2020. p. 16-24 (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS; Vol. 2020-May).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Elessar: Ethics in Norm-Aware Agents

AU - Ajmeri, Nirav

AU - Murukannaiah, P.K.

AU - Guo, Hui

AU - Singh, Munindar P.

N1 - Conference code: 19th

PY - 2020/5

Y1 - 2020/5

N2 - We address the problem of designing agents that navigate social norms by selecting ethically appropriate actions. We present Elessar, a framework in which agents aggregate value preferences of users and select ethically appropriate actions through multicriteria decision making in different social contexts. Via simulations, seeded with a survey of user values and attitudes, we find that Elessar agents act ethically and are effective than baseline agents, in terms of (1) exhibiting the Rawlsian property of fairness, and (2) yielding a satisfactory social experience to users. Our results are stable across agent societies of different sizes and connectedness.

AB - We address the problem of designing agents that navigate social norms by selecting ethically appropriate actions. We present Elessar, a framework in which agents aggregate value preferences of users and select ethically appropriate actions through multicriteria decision making in different social contexts. Via simulations, seeded with a survey of user values and attitudes, we find that Elessar agents act ethically and are effective than baseline agents, in terms of (1) exhibiting the Rawlsian property of fairness, and (2) yielding a satisfactory social experience to users. Our results are stable across agent societies of different sizes and connectedness.

KW - Ethics

KW - Fairness

KW - Preferences

KW - Social norms

KW - Values

UR - http://www.scopus.com/inward/record.url?scp=85092737374&partnerID=8YFLogxK

M3 - Conference contribution

T3 - Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS

SP - 16

EP - 24

BT - Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2020

A2 - An, Bo

A2 - El Fallah Seghrouchni, Amal

A2 - Sukthankar, Gita

T2 - AAMAS 2020

Y2 - 9 May 2020 through 13 May 2020

ER -

Elessar: Ethics in Norm-Aware Agents

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this