Exportar Publicação

Gomes, J., Mariano, P. & Christensen, A. (2015). Cooperative coevolution of partially heterogeneous multiagent systems. In Elkind Bordini, Yolum Weiss (Ed.), Proceedings of the 14th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2015). (pp. 297-305). Istanbul: IFAAMAS.

J. Gomes et al.,  "Cooperative coevolution of partially heterogeneous multiagent systems", in Proc. of the 14th Int. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2015), Elkind Bordini, Yolum Weiss, Ed., Istanbul, IFAAMAS, 2015, vol. 1, pp. 297-305

@inproceedings{gomes2015_1733338429602,
	author = "Gomes, J. and Mariano, P. and Christensen, A.",
	title = "Cooperative coevolution of partially heterogeneous multiagent systems",
	booktitle = "Proceedings of the 14th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2015)",
	year = "2015",
	editor = "Elkind Bordini, Yolum Weiss",
	volume = "1",
	number = "",
	series = "",
	pages = "297-305",
	publisher = "IFAAMAS",
	address = "Istanbul",
	organization = "",
	url = "http://www.aamas2015.com/en/AAMAS_2015_USB/starthere.htm"
}

TY  - CPAPER
TI  - Cooperative coevolution of partially heterogeneous multiagent systems
T2  - Proceedings of the 14th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2015)
VL  - 1
AU  - Gomes, J.
AU  - Mariano, P.
AU  - Christensen, A.
PY  - 2015
SP  - 297-305
CY  - Istanbul
UR  - http://www.aamas2015.com/en/AAMAS_2015_USB/starthere.htm
AB  - Cooperative coevolution algorithms (CCEAs) facilitate the
evolution of heterogeneous, cooperating multiagent systems.
Such algorithms are, however, subject to inherent scalability issues, since the number of required evaluations increases
with the number of agents. A possible solution is to use partially heterogeneous (hybrid) teams: behaviourally heterogeneous teams composed of homogeneous sub-teams. By having different agents share controllers, the number of coevolving populations in the system is reduced. We propose HybCCEA, an extension of cooperative coevolution to partially
heterogeneous multiagent systems. In Hyb-CCEA, both the
agent controllers and the team composition are under evolutionary control. During the evolutionary process, we rely
on measures of behaviour similarity for the formation of homogeneous sub-teams (merging), and propose a stochastic
mechanism to increase heterogeneity (splitting). We evaluate Hyb-CCEA in multiple variants of a simulated herding
task, and compare it with a fully heterogeneous CCEA. Our
results show that Hyb-CCEA can achieve solutions of similar quality using significantly fewer evaluations, and in most
setups, Hyb-CCEA even achieves significantly higher fitness
scores than the CCEA. Overall, we show that merging and
splitting populations are viable mechanisms for the cooperative coevolution of hybrid teams.
ER  -