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

Abstract

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.

Emergence of altruistic behavior in heterogeneous populations of artificial agents by evolution of kin discrimination mechanism

“…Furthermore, even when the option of hunting bigger preys was presented after the hunting behavior had already evolved, cooperation only evolved in 1 of the 30 independent runs. In similar works, when cooperation is the only feasible strategy to perform a task (e.g., Rollins & Schrum, 2017), a team of robots had to hunt preys that were preprogrammed to escape from the nearest predator. The scenario was a torus-shaped grid that allows the prey to move from one edge of the world to the other.…”