Towards a goal-oriented agent-based simulation framework for high-performance computing

Dmitry Gnatyshak; Luis Oliva-Felipe; Sergio Álvarez-Napagao; Julian Padget; Javier Vázquez-Salceda; Dario Garcia-Gasulla; Ulises Cortés

doi:10.3233/FAIA190142

Towards a goal-oriented agent-based simulation framework for high-performance computing

Dmitry Gnatyshak, Luis Oliva-Felipe, Sergio Álvarez-Napagao, Julian Padget, Javier Vázquez-Salceda, Dario Garcia-Gasulla, Ulises Cortés

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

1 Citation (SciVal)

Abstract

Currently, agent-based simulation frameworks force the user to choose between simulations involving a large number of agents (at the expense of limited agent reasoning capability) or simulations including agents with increased reasoning capabilities (at the expense of a limited number of agents per simulation). This paper describes a first attempt at putting goal-oriented agents into large agent-based (micro-)simulations. We discuss a model for goal-oriented agents in High-Performance Computing (HPC) and then briefly discuss its implementation in PyCOMPSs (a library that eases the parallelisation of tasks) to build such a platform that benefits from a large number of agents with the capacity to execute complex cognitive agents.

Original language	English
Title of host publication	Artificial Intelligence Research and Development - Proceedings of the 22nd International Conference of the Catalan Association for Artificial Intelligence, CCIA 2019
Editors	Jordi Sabater-Mir, Vicenc Torra, Isabel Aguilo, Manuel Gonzalez-Hidalgo
Publisher	IOS Press
Pages	329-338
Number of pages	10
ISBN (Electronic)	9781643680149
DOIs	https://doi.org/10.3233/FAIA190142
Publication status	Published - 6 Sept 2019
Event	22nd International Conference of the Catalan Association for Artificial Intelligence, CCIA 2019 - Mallorca, Spain Duration: 23 Oct 2019 → 25 Oct 2019

Publication series

Name	Frontiers in Artificial Intelligence and Applications
Volume	319
ISSN (Print)	0922-6389

Conference

Conference	22nd International Conference of the Catalan Association for Artificial Intelligence, CCIA 2019
Country/Territory	Spain
City	Mallorca
Period	23/10/19 → 25/10/19

Funding

This work is partially supported by the BSC-IBM Deep Learning Center agreement, the Spanish Government through Programa Severo Ochoa (SEV-2015-0493), the 11th call on the Severo Ochoa Mobility Program in BSC, the Spanish Ministry of Science and Technology through TIN2015-65316-P project and the Generalitat de Catalunya (contract 2017-SGR-1414).

Keywords

Agent platform
Agent-based simulation
Goal-oriented agent
High-performance computing
Multi-agent system

ASJC Scopus subject areas

Artificial Intelligence

Access to Document

10.3233/FAIA190142

Cite this

Gnatyshak, D., Oliva-Felipe, L., Álvarez-Napagao, S., Padget, J., Vázquez-Salceda, J., Garcia-Gasulla, D., & Cortés, U. (2019). Towards a goal-oriented agent-based simulation framework for high-performance computing. In J. Sabater-Mir, V. Torra, I. Aguilo, & M. Gonzalez-Hidalgo (Eds.), Artificial Intelligence Research and Development - Proceedings of the 22nd International Conference of the Catalan Association for Artificial Intelligence, CCIA 2019 (pp. 329-338). (Frontiers in Artificial Intelligence and Applications; Vol. 319). IOS Press. https://doi.org/10.3233/FAIA190142

Towards a goal-oriented agent-based simulation framework for high-performance computing. / Gnatyshak, Dmitry; Oliva-Felipe, Luis; Álvarez-Napagao, Sergio et al.
Artificial Intelligence Research and Development - Proceedings of the 22nd International Conference of the Catalan Association for Artificial Intelligence, CCIA 2019. ed. / Jordi Sabater-Mir; Vicenc Torra; Isabel Aguilo; Manuel Gonzalez-Hidalgo. IOS Press, 2019. p. 329-338 (Frontiers in Artificial Intelligence and Applications; Vol. 319).

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

Gnatyshak, D, Oliva-Felipe, L, Álvarez-Napagao, S, Padget, J, Vázquez-Salceda, J, Garcia-Gasulla, D & Cortés, U 2019, Towards a goal-oriented agent-based simulation framework for high-performance computing. in J Sabater-Mir, V Torra, I Aguilo & M Gonzalez-Hidalgo (eds), Artificial Intelligence Research and Development - Proceedings of the 22nd International Conference of the Catalan Association for Artificial Intelligence, CCIA 2019. Frontiers in Artificial Intelligence and Applications, vol. 319, IOS Press, pp. 329-338, 22nd International Conference of the Catalan Association for Artificial Intelligence, CCIA 2019, Mallorca, Spain, 23/10/19. https://doi.org/10.3233/FAIA190142

Gnatyshak D, Oliva-Felipe L, Álvarez-Napagao S, Padget J, Vázquez-Salceda J, Garcia-Gasulla D et al. Towards a goal-oriented agent-based simulation framework for high-performance computing. In Sabater-Mir J, Torra V, Aguilo I, Gonzalez-Hidalgo M, editors, Artificial Intelligence Research and Development - Proceedings of the 22nd International Conference of the Catalan Association for Artificial Intelligence, CCIA 2019. IOS Press. 2019. p. 329-338. (Frontiers in Artificial Intelligence and Applications). doi: 10.3233/FAIA190142

Gnatyshak, Dmitry ; Oliva-Felipe, Luis ; Álvarez-Napagao, Sergio et al. / Towards a goal-oriented agent-based simulation framework for high-performance computing. Artificial Intelligence Research and Development - Proceedings of the 22nd International Conference of the Catalan Association for Artificial Intelligence, CCIA 2019. editor / Jordi Sabater-Mir ; Vicenc Torra ; Isabel Aguilo ; Manuel Gonzalez-Hidalgo. IOS Press, 2019. pp. 329-338 (Frontiers in Artificial Intelligence and Applications).

@inproceedings{8cf0496a763a44a78df9f17cfe0d1223,

title = "Towards a goal-oriented agent-based simulation framework for high-performance computing",

abstract = "Currently, agent-based simulation frameworks force the user to choose between simulations involving a large number of agents (at the expense of limited agent reasoning capability) or simulations including agents with increased reasoning capabilities (at the expense of a limited number of agents per simulation). This paper describes a first attempt at putting goal-oriented agents into large agent-based (micro-)simulations. We discuss a model for goal-oriented agents in High-Performance Computing (HPC) and then briefly discuss its implementation in PyCOMPSs (a library that eases the parallelisation of tasks) to build such a platform that benefits from a large number of agents with the capacity to execute complex cognitive agents.",

keywords = "Agent platform, Agent-based simulation, Goal-oriented agent, High-performance computing, Multi-agent system",

author = "Dmitry Gnatyshak and Luis Oliva-Felipe and Sergio {\'A}lvarez-Napagao and Julian Padget and Javier V{\'a}zquez-Salceda and Dario Garcia-Gasulla and Ulises Cort{\'e}s",

year = "2019",

month = sep,

day = "6",

doi = "10.3233/FAIA190142",

language = "English",

series = "Frontiers in Artificial Intelligence and Applications",

publisher = "IOS Press",

pages = "329--338",

editor = "Jordi Sabater-Mir and Vicenc Torra and Isabel Aguilo and Manuel Gonzalez-Hidalgo",

booktitle = "Artificial Intelligence Research and Development - Proceedings of the 22nd International Conference of the Catalan Association for Artificial Intelligence, CCIA 2019",

address = "Netherlands",

note = "22nd International Conference of the Catalan Association for Artificial Intelligence, CCIA 2019 ; Conference date: 23-10-2019 Through 25-10-2019",

}

TY - GEN

T1 - Towards a goal-oriented agent-based simulation framework for high-performance computing

AU - Gnatyshak, Dmitry

AU - Oliva-Felipe, Luis

AU - Álvarez-Napagao, Sergio

AU - Padget, Julian

AU - Vázquez-Salceda, Javier

AU - Garcia-Gasulla, Dario

AU - Cortés, Ulises

PY - 2019/9/6

Y1 - 2019/9/6

N2 - Currently, agent-based simulation frameworks force the user to choose between simulations involving a large number of agents (at the expense of limited agent reasoning capability) or simulations including agents with increased reasoning capabilities (at the expense of a limited number of agents per simulation). This paper describes a first attempt at putting goal-oriented agents into large agent-based (micro-)simulations. We discuss a model for goal-oriented agents in High-Performance Computing (HPC) and then briefly discuss its implementation in PyCOMPSs (a library that eases the parallelisation of tasks) to build such a platform that benefits from a large number of agents with the capacity to execute complex cognitive agents.

AB - Currently, agent-based simulation frameworks force the user to choose between simulations involving a large number of agents (at the expense of limited agent reasoning capability) or simulations including agents with increased reasoning capabilities (at the expense of a limited number of agents per simulation). This paper describes a first attempt at putting goal-oriented agents into large agent-based (micro-)simulations. We discuss a model for goal-oriented agents in High-Performance Computing (HPC) and then briefly discuss its implementation in PyCOMPSs (a library that eases the parallelisation of tasks) to build such a platform that benefits from a large number of agents with the capacity to execute complex cognitive agents.

KW - Agent platform

KW - Agent-based simulation

KW - Goal-oriented agent

KW - High-performance computing

KW - Multi-agent system

UR - https://www.scopus.com/pages/publications/85085017506

U2 - 10.3233/FAIA190142

DO - 10.3233/FAIA190142

M3 - Chapter in a published conference proceeding

AN - SCOPUS:85085017506

T3 - Frontiers in Artificial Intelligence and Applications

SP - 329

EP - 338

BT - Artificial Intelligence Research and Development - Proceedings of the 22nd International Conference of the Catalan Association for Artificial Intelligence, CCIA 2019

A2 - Sabater-Mir, Jordi

A2 - Torra, Vicenc

A2 - Aguilo, Isabel

A2 - Gonzalez-Hidalgo, Manuel

PB - IOS Press

T2 - 22nd International Conference of the Catalan Association for Artificial Intelligence, CCIA 2019

Y2 - 23 October 2019 through 25 October 2019

ER -

Towards a goal-oriented agent-based simulation framework for high-performance computing

Abstract

Publication series

Conference

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this