Approaches to dynamic team sizes

Nitschke, Geoff; Tolkamp, S. M.

doi:10.1109/riiss.2013.6607931

Cited by 2 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the teams in this paper are heterogeneous, in contrast to those from the Fight or Flight study [19]. However, the previously mentioned research indicating that heterogeneous teams from a single population perform poorly in cooperative tasks [6,27] does not apply to these teams, because selecting individual team members from specific sub-populations allows them to specialize in a way that actually promotes cooperation [7,15,13,14]. Such cooperation is necessary for a team of evolved predator agents to capture fleeing prey agents in the domain described next.…”

Section: Introductionmentioning

confidence: 90%

Balancing selection pressures, multiple objectives, and neural modularity to coevolve cooperative agent behavior

Rollins¹,

Schrum²

2017

Proceedings of the Genetic and Evolutionary Computation Conference Companion

View full text Add to dashboard Cite

Previous research using evolutionary computation inMulti-Agent Systems indicates that assigning fitness based on team vs. individual behavior has a strong impact on the ability of evolved teams of artificial agents to exhibit teamwork in challenging tasks. However, such research only made use of single-objective evolution. In contrast, when a multiobjective evolutionary algorithm is used, populations can be subject to individual-level objectives, team-level objectives, or combinations of the two. This paper explores the performance of cooperatively coevolved teams of agents controlled by artificial neural networks subject to these types of objectives. Specifically, predator agents are evolved to capture scripted prey agents in a torus-shaped grid world. Because of the tension between individual and team behaviors, multiple modes of behavior can be useful, and thus the effect of modular neural networks is also explored. Results demonstrate that fitness rewarding individual behavior is superior to fitness rewarding team behavior, despite being applied to a cooperative task. However, the use of networks with multiple modules allows predators to discover intelligent behavior, regardless of which type of objectives are used.

show abstract