Emergence of efficient, coordinated solutions despite differences in agent ability during human-machine interaction: demonstration using a multiagent “shepherding” task

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

Abstract

Working with others not only improves behavioral efficiency, but also facilitates learning. Such multiagent activity is fundamental to everyday life and, increasingly, virtual and robotic agents are finding a place in these contexts. The effectiveness of human-machine interaction (HMI), however, relies on artificial systems being able to anticipate their partner and select actions that not only lead to achieving the shared goal, but does so efficiently. Here, a multiagent “shepherding” task was used to study coordination and behavior-switching during HMI. The task required the coordinated control of a complex environment, where a non-obvious solution leads to near-optimal task performance. Previous research has demonstrated that a virtual agent, with knowledge of the optimal solution, can effectively steer novices to discover the optimal task behavior [3]. Conversely, results here demonstrate that when completing the task with a virtual avatar incapable of producing this behavior, a subset of novices still discovered and enforced this optimal behavior in the virtual avatar by modulating the sheep-herd’s dynamics. These results provide evidence that learning efficient solutions may result from interaction patterns early in the interaction, which may be exploited by adaptive artificial-agents in HMI contexts to facilitate skill acquisition.

LanguageEnglish
Title of host publicationProceedings of the 18th International Conference on Intelligent Virtual Agents (IVA 2018)
Place of PublicationNew York
PublisherAssociation for Computing Machinery, Inc
Pages337-338
Number of pages2
ISBN (Electronic)9781450360135
DOIs
Publication statusPublished - 2018
Event18th ACM International Conference on Intelligent Virtual Agents, IVA 2018 - Sydney, Australia
Duration: 5 Nov 20188 Nov 2018

Conference

Conference18th ACM International Conference on Intelligent Virtual Agents, IVA 2018
CountryAustralia
CitySydney
Period5/11/188/11/18

Fingerprint

Demonstrations
Robotics

Keywords

  • multiagent coordination
  • problem-solving
  • human-machine interaction

Cite this

Nalepka, P., Lamb, M., Kallen, R. W., & Richardson, M. J. (2018). Emergence of efficient, coordinated solutions despite differences in agent ability during human-machine interaction: demonstration using a multiagent “shepherding” task. In Proceedings of the 18th International Conference on Intelligent Virtual Agents (IVA 2018) (pp. 337-338). New York: Association for Computing Machinery, Inc. https://doi.org/10.1145/3267851.3267879
Nalepka, Patrick ; Lamb, Maurice ; Kallen, Rachel W. ; Richardson, Michael J. / Emergence of efficient, coordinated solutions despite differences in agent ability during human-machine interaction : demonstration using a multiagent “shepherding” task. Proceedings of the 18th International Conference on Intelligent Virtual Agents (IVA 2018). New York : Association for Computing Machinery, Inc, 2018. pp. 337-338
@inproceedings{9057dbeda69a4a2eb1e00aa578f3487e,
title = "Emergence of efficient, coordinated solutions despite differences in agent ability during human-machine interaction: demonstration using a multiagent “shepherding” task",
abstract = "Working with others not only improves behavioral efficiency, but also facilitates learning. Such multiagent activity is fundamental to everyday life and, increasingly, virtual and robotic agents are finding a place in these contexts. The effectiveness of human-machine interaction (HMI), however, relies on artificial systems being able to anticipate their partner and select actions that not only lead to achieving the shared goal, but does so efficiently. Here, a multiagent “shepherding” task was used to study coordination and behavior-switching during HMI. The task required the coordinated control of a complex environment, where a non-obvious solution leads to near-optimal task performance. Previous research has demonstrated that a virtual agent, with knowledge of the optimal solution, can effectively steer novices to discover the optimal task behavior [3]. Conversely, results here demonstrate that when completing the task with a virtual avatar incapable of producing this behavior, a subset of novices still discovered and enforced this optimal behavior in the virtual avatar by modulating the sheep-herd’s dynamics. These results provide evidence that learning efficient solutions may result from interaction patterns early in the interaction, which may be exploited by adaptive artificial-agents in HMI contexts to facilitate skill acquisition.",
keywords = "multiagent coordination, problem-solving, human-machine interaction",
author = "Patrick Nalepka and Maurice Lamb and Kallen, {Rachel W.} and Richardson, {Michael J.}",
year = "2018",
doi = "10.1145/3267851.3267879",
language = "English",
pages = "337--338",
booktitle = "Proceedings of the 18th International Conference on Intelligent Virtual Agents (IVA 2018)",
publisher = "Association for Computing Machinery, Inc",

}

Nalepka, P, Lamb, M, Kallen, RW & Richardson, MJ 2018, Emergence of efficient, coordinated solutions despite differences in agent ability during human-machine interaction: demonstration using a multiagent “shepherding” task. in Proceedings of the 18th International Conference on Intelligent Virtual Agents (IVA 2018). Association for Computing Machinery, Inc, New York, pp. 337-338, 18th ACM International Conference on Intelligent Virtual Agents, IVA 2018, Sydney, Australia, 5/11/18. https://doi.org/10.1145/3267851.3267879

Emergence of efficient, coordinated solutions despite differences in agent ability during human-machine interaction : demonstration using a multiagent “shepherding” task. / Nalepka, Patrick; Lamb, Maurice; Kallen, Rachel W.; Richardson, Michael J.

Proceedings of the 18th International Conference on Intelligent Virtual Agents (IVA 2018). New York : Association for Computing Machinery, Inc, 2018. p. 337-338.

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

TY - GEN

T1 - Emergence of efficient, coordinated solutions despite differences in agent ability during human-machine interaction

T2 - demonstration using a multiagent “shepherding” task

AU - Nalepka, Patrick

AU - Lamb, Maurice

AU - Kallen, Rachel W.

AU - Richardson, Michael J.

PY - 2018

Y1 - 2018

N2 - Working with others not only improves behavioral efficiency, but also facilitates learning. Such multiagent activity is fundamental to everyday life and, increasingly, virtual and robotic agents are finding a place in these contexts. The effectiveness of human-machine interaction (HMI), however, relies on artificial systems being able to anticipate their partner and select actions that not only lead to achieving the shared goal, but does so efficiently. Here, a multiagent “shepherding” task was used to study coordination and behavior-switching during HMI. The task required the coordinated control of a complex environment, where a non-obvious solution leads to near-optimal task performance. Previous research has demonstrated that a virtual agent, with knowledge of the optimal solution, can effectively steer novices to discover the optimal task behavior [3]. Conversely, results here demonstrate that when completing the task with a virtual avatar incapable of producing this behavior, a subset of novices still discovered and enforced this optimal behavior in the virtual avatar by modulating the sheep-herd’s dynamics. These results provide evidence that learning efficient solutions may result from interaction patterns early in the interaction, which may be exploited by adaptive artificial-agents in HMI contexts to facilitate skill acquisition.

AB - Working with others not only improves behavioral efficiency, but also facilitates learning. Such multiagent activity is fundamental to everyday life and, increasingly, virtual and robotic agents are finding a place in these contexts. The effectiveness of human-machine interaction (HMI), however, relies on artificial systems being able to anticipate their partner and select actions that not only lead to achieving the shared goal, but does so efficiently. Here, a multiagent “shepherding” task was used to study coordination and behavior-switching during HMI. The task required the coordinated control of a complex environment, where a non-obvious solution leads to near-optimal task performance. Previous research has demonstrated that a virtual agent, with knowledge of the optimal solution, can effectively steer novices to discover the optimal task behavior [3]. Conversely, results here demonstrate that when completing the task with a virtual avatar incapable of producing this behavior, a subset of novices still discovered and enforced this optimal behavior in the virtual avatar by modulating the sheep-herd’s dynamics. These results provide evidence that learning efficient solutions may result from interaction patterns early in the interaction, which may be exploited by adaptive artificial-agents in HMI contexts to facilitate skill acquisition.

KW - multiagent coordination

KW - problem-solving

KW - human-machine interaction

UR - http://www.scopus.com/inward/record.url?scp=85058448182&partnerID=8YFLogxK

UR - http://iva2018.westernsydney.edu.au/

U2 - 10.1145/3267851.3267879

DO - 10.1145/3267851.3267879

M3 - Conference proceeding contribution

SP - 337

EP - 338

BT - Proceedings of the 18th International Conference on Intelligent Virtual Agents (IVA 2018)

PB - Association for Computing Machinery, Inc

CY - New York

ER -

Nalepka P, Lamb M, Kallen RW, Richardson MJ. Emergence of efficient, coordinated solutions despite differences in agent ability during human-machine interaction: demonstration using a multiagent “shepherding” task. In Proceedings of the 18th International Conference on Intelligent Virtual Agents (IVA 2018). New York: Association for Computing Machinery, Inc. 2018. p. 337-338 https://doi.org/10.1145/3267851.3267879