Emergence of Norms in Interactions with Complex Rewards

Dhaminda B Abeywickrama; Nathan Griffiths; Zhou Xu; Alex Mouzakitis

Emergence of Norms in Interactions with Complex Rewards

Dhaminda B Abeywickrama^*
, Nathan Griffiths
, Zhou Xu
, Alex Mouzakitis

^*Corresponding author for this work

School of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

Abstract

Autonomous systems are becoming pervasive, and as they become applied to highly dynamic and heterogeneous environments there is a need to model and understand more complex and nuanced agent interactions than have been previously studied. This paper proposes an agent-based modelling approach, based on norm emergence, to investigate such interactions. While there is typically an ideal set of compatible actions which lead to an optimal norm, in complex environments there may also be combinations that are compatible and yield positive (but not optimal) rewards. We illustrate our model of such scenarios using the case of an autonomous vehicle performing a manoeuvre at a T-intersection.

Original language	English
Title of host publication	Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems
Place of Publication	Richland, SC
Publisher	International Foundation for Autonomous Agents and MultiAgent Systems
Pages	2280–2282
Number of pages	3
ISBN (Electronic)	9781450394321
Publication status	Published - 2 Jun 2023

Publication series

Name	AAMAS Conference proceedings
ISSN (Print)	2523-5699

Name	Proceedings of International Conference on Autonomous Agents and Multiagent Systems
ISSN (Print)	2523-5699

Keywords

Agent Interactions
Norm Emergence
Reinforcement Learning

Access to Document

https://dl.acm.org/doi/10.5555/3545946.3598906Licence: Unspecified

Handle.net

Persistent link

UKRI Trustworthy Autonomous Systems Node In Functionality
Windsor, S. P. (Principal Investigator), Ives, J. C. S. (Co-Investigator), Downer, J. R. (Co-Investigator), Rossiter, J. M. (Co-Investigator), Eder, K. I. (Co-Investigator) & Hauert, S. (Co-Investigator)
1/11/20 → 30/04/24
Project: Research, Parent

Cite this

Abeywickrama, D. B., Griffiths, N., Xu, Z., & Mouzakitis, A. (2023). Emergence of Norms in Interactions with Complex Rewards. In Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems (pp. 2280–2282). (AAMAS Conference proceedings), (Proceedings of International Conference on Autonomous Agents and Multiagent Systems). International Foundation for Autonomous Agents and MultiAgent Systems. https://dl.acm.org/doi/10.5555/3545946.3598906

Abeywickrama, Dhaminda B ; Griffiths, Nathan ; Xu, Zhou et al. / Emergence of Norms in Interactions with Complex Rewards. Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems. Richland, SC : International Foundation for Autonomous Agents and MultiAgent Systems, 2023. pp. 2280–2282 (AAMAS Conference proceedings). (Proceedings of International Conference on Autonomous Agents and Multiagent Systems).

@inproceedings{f974a3c75ab94a2ba56745a6bc012538,

title = "Emergence of Norms in Interactions with Complex Rewards",

abstract = "Autonomous systems are becoming pervasive, and as they become applied to highly dynamic and heterogeneous environments there is a need to model and understand more complex and nuanced agent interactions than have been previously studied. This paper proposes an agent-based modelling approach, based on norm emergence, to investigate such interactions. While there is typically an ideal set of compatible actions which lead to an optimal norm, in complex environments there may also be combinations that are compatible and yield positive (but not optimal) rewards. We illustrate our model of such scenarios using the case of an autonomous vehicle performing a manoeuvre at a T-intersection.",

keywords = "Agent Interactions, Norm Emergence, Reinforcement Learning",

author = "Abeywickrama, \{Dhaminda B\} and Nathan Griffiths and Zhou Xu and Alex Mouzakitis",

year = "2023",

month = jun,

day = "2",

language = "English",

series = "AAMAS Conference proceedings",

publisher = "International Foundation for Autonomous Agents and MultiAgent Systems",

pages = "2280–2282",

booktitle = "Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems",

}

Abeywickrama, DB, Griffiths, N, Xu, Z & Mouzakitis, A 2023, Emergence of Norms in Interactions with Complex Rewards. in Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems. AAMAS Conference proceedings, Proceedings of International Conference on Autonomous Agents and Multiagent Systems, International Foundation for Autonomous Agents and MultiAgent Systems, Richland, SC, pp. 2280–2282. <https://dl.acm.org/doi/10.5555/3545946.3598906>

Emergence of Norms in Interactions with Complex Rewards. / Abeywickrama, Dhaminda B; Griffiths, Nathan; Xu, Zhou et al.
Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems. Richland, SC: International Foundation for Autonomous Agents and MultiAgent Systems, 2023. p. 2280–2282 (AAMAS Conference proceedings), (Proceedings of International Conference on Autonomous Agents and Multiagent Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Emergence of Norms in Interactions with Complex Rewards

AU - Abeywickrama, Dhaminda B

AU - Griffiths, Nathan

AU - Xu, Zhou

AU - Mouzakitis, Alex

PY - 2023/6/2

Y1 - 2023/6/2

N2 - Autonomous systems are becoming pervasive, and as they become applied to highly dynamic and heterogeneous environments there is a need to model and understand more complex and nuanced agent interactions than have been previously studied. This paper proposes an agent-based modelling approach, based on norm emergence, to investigate such interactions. While there is typically an ideal set of compatible actions which lead to an optimal norm, in complex environments there may also be combinations that are compatible and yield positive (but not optimal) rewards. We illustrate our model of such scenarios using the case of an autonomous vehicle performing a manoeuvre at a T-intersection.

AB - Autonomous systems are becoming pervasive, and as they become applied to highly dynamic and heterogeneous environments there is a need to model and understand more complex and nuanced agent interactions than have been previously studied. This paper proposes an agent-based modelling approach, based on norm emergence, to investigate such interactions. While there is typically an ideal set of compatible actions which lead to an optimal norm, in complex environments there may also be combinations that are compatible and yield positive (but not optimal) rewards. We illustrate our model of such scenarios using the case of an autonomous vehicle performing a manoeuvre at a T-intersection.

KW - Agent Interactions

KW - Norm Emergence

KW - Reinforcement Learning

M3 - Conference Contribution (Conference Proceeding)

T3 - AAMAS Conference proceedings

SP - 2280

EP - 2282

BT - Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems

PB - International Foundation for Autonomous Agents and MultiAgent Systems

CY - Richland, SC

ER -

Abeywickrama DB, Griffiths N, Xu Z, Mouzakitis A. Emergence of Norms in Interactions with Complex Rewards. In Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems. Richland, SC: International Foundation for Autonomous Agents and MultiAgent Systems. 2023. p. 2280–2282. (AAMAS Conference proceedings). (Proceedings of International Conference on Autonomous Agents and Multiagent Systems).

Emergence of Norms in Interactions with Complex Rewards

Abstract

Publication series

Keywords

Access to Document

Handle.net

Fingerprint

Projects

UKRI Trustworthy Autonomous Systems Node In Functionality

Cite this