Training with automated agents improves people's behavior in negotiation and coordination tasks

Raz Lin; Ya'Akov Gal; Sarit Kraus; Yaniv Mazliah

doi:10.1016/j.dss.2013.05.015

Training with automated agents improves people's behavior in negotiation and coordination tasks

Raz Lin, Ya'Akov Gal, Sarit Kraus, Yaniv Mazliah

Department of Computer Science

Research output: Contribution to journal › Article › peer-review

44 Scopus citations

Abstract

There is inconclusive evidence whether practicing tasks with computer agents improves people's performance on these tasks. This paper studies this question empirically using extensive experiments involving bilateral negotiation and three-player coordination tasks played by hundreds of human subjects. We used different training methods for subjects, including practice interactions with other human participants, interacting with agents from the literature, and asking participants to design an automated agent to serve as their proxy in the task. Following training, we compared the performance of subjects when playing state-of-the-art agents from the literature. The results revealed that in the negotiation settings, in most cases, training with computer agents increased people's performance as compared to interacting with people. In the three player coordination game, training with computer agents increased people's performance when matched with the state-of-the-art agent. These results demonstrate the efficacy of using computer agents as tools for improving people's skills when interacting in strategic settings, saving considerable effort and providing better performance than when interacting with human counterparts.

Original language	English
Pages (from-to)	1-9
Number of pages	9
Journal	Decision Support Systems
Volume	60
Issue number	1
DOIs	https://doi.org/10.1016/j.dss.2013.05.015
State	Published - Apr 2014

Bibliographical note

Funding Information:
This research is supported in part by the U.S. Army Research Laboratory and the U.S. Army Research Office under grant number W911NF-08-1-0144 , under MURI grant number W911NF-08-1-0144 , by ERC grant # 267523 and by the Google Interuniversity center for Electronic Markets and Auctions . Y.G. was supported in part by Marie Curie grant number # 268362 .

Funding Information:
Ya'akov (Kobi) Gal is a faculty member of the Department of Information Systems Engineering at the Ben-Gurion University of the Negev, and an associate at the School of Engineering and Applied Sciences at Harvard University. His work investigates representations and algorithms for making decisions in heterogeneous groups comprising both people and computational agents. He has published over 40 papers in highly refereed venues on topics ranging from artificial intelligence to the learning and cognitive sciences. He is a recipient of the Wolf foundation's 2013 Krill prize for young Israeli scientists, a Marie Curie International fellowship for 2010, a two-time recipient of Harvard University's Derek Bok award for excellence in teaching, as well as the School of Engineering and Applied Science's outstanding teacher award.

Funding

This research is supported in part by the U.S. Army Research Laboratory and the U.S. Army Research Office under grant number W911NF-08-1-0144 , under MURI grant number W911NF-08-1-0144 , by ERC grant # 267523 and by the Google Interuniversity center for Electronic Markets and Auctions . Y.G. was supported in part by Marie Curie grant number # 268362 . Ya'akov (Kobi) Gal is a faculty member of the Department of Information Systems Engineering at the Ben-Gurion University of the Negev, and an associate at the School of Engineering and Applied Sciences at Harvard University. His work investigates representations and algorithms for making decisions in heterogeneous groups comprising both people and computational agents. He has published over 40 papers in highly refereed venues on topics ranging from artificial intelligence to the learning and cognitive sciences. He is a recipient of the Wolf foundation's 2013 Krill prize for young Israeli scientists, a Marie Curie International fellowship for 2010, a two-time recipient of Harvard University's Derek Bok award for excellence in teaching, as well as the School of Engineering and Applied Science's outstanding teacher award.

Funders	Funder number
Google Interuniversity center for Electronic Markets and Auctions
U.S. Army Research Office	W911NF-08-1-0144
Army Research Laboratory
Harvard University
Fu Foundation School of Engineering and Applied Science
Seventh Framework Programme	267523, 268362
Multidisciplinary University Research Initiative
Marie Curie
European Commission

Keywords

Automated agents
Automated negotiation
Coordination
Training

Access to Document

10.1016/j.dss.2013.05.015

Cite this

@article{91eeb1f51b1a42b3a101264337fd8bb4,

title = "Training with automated agents improves people's behavior in negotiation and coordination tasks",

abstract = "There is inconclusive evidence whether practicing tasks with computer agents improves people's performance on these tasks. This paper studies this question empirically using extensive experiments involving bilateral negotiation and three-player coordination tasks played by hundreds of human subjects. We used different training methods for subjects, including practice interactions with other human participants, interacting with agents from the literature, and asking participants to design an automated agent to serve as their proxy in the task. Following training, we compared the performance of subjects when playing state-of-the-art agents from the literature. The results revealed that in the negotiation settings, in most cases, training with computer agents increased people's performance as compared to interacting with people. In the three player coordination game, training with computer agents increased people's performance when matched with the state-of-the-art agent. These results demonstrate the efficacy of using computer agents as tools for improving people's skills when interacting in strategic settings, saving considerable effort and providing better performance than when interacting with human counterparts.",

keywords = "Automated agents, Automated negotiation, Coordination, Training",

author = "Raz Lin and Ya'Akov Gal and Sarit Kraus and Yaniv Mazliah",

note = "Funding Information: This research is supported in part by the U.S. Army Research Laboratory and the U.S. Army Research Office under grant number W911NF-08-1-0144 , under MURI grant number W911NF-08-1-0144 , by ERC grant # 267523 and by the Google Interuniversity center for Electronic Markets and Auctions . Y.G. was supported in part by Marie Curie grant number # 268362 . Funding Information: Ya'akov (Kobi) Gal is a faculty member of the Department of Information Systems Engineering at the Ben-Gurion University of the Negev, and an associate at the School of Engineering and Applied Sciences at Harvard University. His work investigates representations and algorithms for making decisions in heterogeneous groups comprising both people and computational agents. He has published over 40 papers in highly refereed venues on topics ranging from artificial intelligence to the learning and cognitive sciences. He is a recipient of the Wolf foundation's 2013 Krill prize for young Israeli scientists, a Marie Curie International fellowship for 2010, a two-time recipient of Harvard University's Derek Bok award for excellence in teaching, as well as the School of Engineering and Applied Science's outstanding teacher award. ",

year = "2014",

month = apr,

doi = "10.1016/j.dss.2013.05.015",

language = "אנגלית",

volume = "60",

pages = "1--9",

journal = "Decision Support Systems",

issn = "0167-9236",

publisher = "Elsevier B.V.",

number = "1",

}

TY - JOUR

T1 - Training with automated agents improves people's behavior in negotiation and coordination tasks

AU - Lin, Raz

AU - Gal, Ya'Akov

AU - Kraus, Sarit

AU - Mazliah, Yaniv

N1 - Funding Information: This research is supported in part by the U.S. Army Research Laboratory and the U.S. Army Research Office under grant number W911NF-08-1-0144 , under MURI grant number W911NF-08-1-0144 , by ERC grant # 267523 and by the Google Interuniversity center for Electronic Markets and Auctions . Y.G. was supported in part by Marie Curie grant number # 268362 . Funding Information: Ya'akov (Kobi) Gal is a faculty member of the Department of Information Systems Engineering at the Ben-Gurion University of the Negev, and an associate at the School of Engineering and Applied Sciences at Harvard University. His work investigates representations and algorithms for making decisions in heterogeneous groups comprising both people and computational agents. He has published over 40 papers in highly refereed venues on topics ranging from artificial intelligence to the learning and cognitive sciences. He is a recipient of the Wolf foundation's 2013 Krill prize for young Israeli scientists, a Marie Curie International fellowship for 2010, a two-time recipient of Harvard University's Derek Bok award for excellence in teaching, as well as the School of Engineering and Applied Science's outstanding teacher award.

PY - 2014/4

Y1 - 2014/4

N2 - There is inconclusive evidence whether practicing tasks with computer agents improves people's performance on these tasks. This paper studies this question empirically using extensive experiments involving bilateral negotiation and three-player coordination tasks played by hundreds of human subjects. We used different training methods for subjects, including practice interactions with other human participants, interacting with agents from the literature, and asking participants to design an automated agent to serve as their proxy in the task. Following training, we compared the performance of subjects when playing state-of-the-art agents from the literature. The results revealed that in the negotiation settings, in most cases, training with computer agents increased people's performance as compared to interacting with people. In the three player coordination game, training with computer agents increased people's performance when matched with the state-of-the-art agent. These results demonstrate the efficacy of using computer agents as tools for improving people's skills when interacting in strategic settings, saving considerable effort and providing better performance than when interacting with human counterparts.

AB - There is inconclusive evidence whether practicing tasks with computer agents improves people's performance on these tasks. This paper studies this question empirically using extensive experiments involving bilateral negotiation and three-player coordination tasks played by hundreds of human subjects. We used different training methods for subjects, including practice interactions with other human participants, interacting with agents from the literature, and asking participants to design an automated agent to serve as their proxy in the task. Following training, we compared the performance of subjects when playing state-of-the-art agents from the literature. The results revealed that in the negotiation settings, in most cases, training with computer agents increased people's performance as compared to interacting with people. In the three player coordination game, training with computer agents increased people's performance when matched with the state-of-the-art agent. These results demonstrate the efficacy of using computer agents as tools for improving people's skills when interacting in strategic settings, saving considerable effort and providing better performance than when interacting with human counterparts.

KW - Automated agents

KW - Automated negotiation

KW - Coordination

KW - Training

UR - http://www.scopus.com/inward/record.url?scp=84897113261&partnerID=8YFLogxK

U2 - 10.1016/j.dss.2013.05.015

DO - 10.1016/j.dss.2013.05.015

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:84897113261

SN - 0167-9236

VL - 60

SP - 1

EP - 9

JO - Decision Support Systems

JF - Decision Support Systems

IS - 1

ER -

Training with automated agents improves people's behavior in negotiation and coordination tasks

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this