Abstract
Understanding the relationship between model complexity and fidelity in simulations is particularly important as increased complexity is one of the major cost drivers of any simulation. In this work we explore the relationship between complexity and fidelity in simple rule based multi-agent systems by employing a multi-objective evolutionary framework in two problem domains: (1) Simulation of conversational group dynamics (2) Simulation of sheepdog herding dynamics. Firstly, a new complexity measure is introduced to characterise complexity of the multi-agent systems. Thereafter the interplay between complexity and fidelity is analysed and the relationship is derived empirically by fitting the obtained data into functions that can describe the relationship in a compact and meaningful manner. This empirical study will be useful to develop theoretical understandings of the complexity and fidelity trade-off in multi-agent based simulations and the approach may be generalised to other simulation types.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
The repel from the dog rule has two different implementations based on the parameter choices and these two implementations are mutually exclusive in a given simulation.
- 2.
Fidelity values show minor variations between the runs due to different seeds fed into the starting configuration.
References
Brooks, R. and Tobias, A.: Choosing the best model: Level of detail, complexity, and model performance. Math. Comput. Model, 24(4), 1–14 (1996)
Chwif, L., Barretto, M. R. P., and Paul, R. J.: On simulation model complexity. In: 2000 Winter Simulation Conference, volume 1, pp. 449–455. IEEE (2000)
Robinson, S.: Tutorial: Choosing what to model—conceptual modeling for simulation. In: 2012 Winter Simulation Conference (WSC), pp. 1–12. IEEE (2012)
Amin, R., Tang, J., Ellejmi, M., Kirby, S., and Abbass, H. A.: Trading-off simulation fidelity and optimization accuracy in air-traffic experiments using differential evolution. In: 2014 IEEE Congress on Evolutionary Computation, pp. 475–482. IEEE. (2014)
Lakshika, E., Barlow, M., and Easton, A.: Understanding the interplay of model complexity and fidelity in multi-agent systems via an evolutionary framework. IEEE Trans. Comput. Intell. AI in Games, doi:10.1109/TCIAIG.2016.2560882, IEEE (in press)
Konak, A., Coit, D. W., and Smith, A. E.: Multi-objective optimization using genetic algorithms: A tutorial. Reliab. Eng. Syst. Safe., 91(9), 992–1007 (2006)
McCabe, T. J.: A complexity measure. IEEE Trans. Softw. Eng., 2(4), 308–320 (1976)
Robinson, S.: Conceptual modelling for simulation part I: definition and requirements. J. Oper. Res. Soc., 59(3), 278–290 (2007)
Yilmaz, L., ren, T., and Aghaee, N.-G.: Intelligent agents, simulation, and gaming. Simul. Gaming, 37(3), 339–349 (2006)
Moore, G. E.: Cramming More Components onto Integrated Circuits. Electronics, 38(8), 114–117 (1965)
Mack, C. A.: Fifty Years of Moores Law. IEEE Trans. Semicond. Manuf., 24(2), 202–207 (2011)
Brom, C., Ser’y, O., and Poch, T.: Simulation level of detail for virtual humans. In: 7th international conference on Intelligent Virtual Agents, pages 1–14. Springer (2007)
Gross, D. C. et al.: Report from the fidelity implementation study group. In: Fall Simulation Interoperability Workshop Papers. (1999)
Lakshika, E., Barlow, M., and Easton, A. : Fidelity and complexity of standing group conversation simulations: A framework for the evolution of multi agent systems through bootstrapping human aesthetic judgments. In: 2012 IEEE Congress on Evolutionary Computation (CEC), pp. 1044–1051 (2012)
Deb, K., Pratap, A., Agarwal, S., and Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: Nsga-II. IEEE Trans. Evol. Comput., 6(2):182–197 (2002)
Lakshika, E., Barlow, M., and Easton, A.: Evolving high fidelity low complexity sheepdog herding simulations using a machine learner fitness function surrogate for human judgement. In: Australasian Joint Conference on Artificial Intelligence, pp. 330–342. Springer (2015)
Smola, A. J. and Scholkopf, B.: A tutorial on support vector regression. Stat. Comput., 14(3):199–222 (2004)
Witten, I. H. and Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems). Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (2005)
Lakshika, E.: An exploration of the complexity-fidelity trade-off in multi-agent systems via an evolutionary framework. Phd thesis, Engineering & Information Technology, University of New South Wales, Canberra, Australia (2014)
Richards, F. : A flexible growth function for empirical use. J. Exp. Bot., 10(2):290–301 (1959)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Lakshika, E., Barlow, M. (2017). On Deriving a Relationship Between Complexity and Fidelity in Rule Based Multi-agent Systems. In: Leu, G., Singh, H., Elsayed, S. (eds) Intelligent and Evolutionary Systems. Proceedings in Adaptation, Learning and Optimization, vol 8. Springer, Cham. https://doi.org/10.1007/978-3-319-49049-6_16
Download citation
DOI: https://doi.org/10.1007/978-3-319-49049-6_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-49048-9
Online ISBN: 978-3-319-49049-6
eBook Packages: EngineeringEngineering (R0)