Evolution of Collective AI Beyond Individual Optimization
Ryosuke Takata, Yujin Tang, Yingtao Tian, Norihiro Maruyama, Hiroki, Kojima, Takashi Ikegami

TL;DR
This paper explores how collective behaviors emerge from homogeneous agents optimized for specific tasks, revealing that over-optimization can reduce group effectiveness due to reduced sensor-motor coupling.
Contribution
It demonstrates the evolution of collective behaviors from simple neural agents and highlights the impact of individual differentiation on group performance.
Findings
Population differentiation occurs during evolution.
Collective fitness can decline despite high individual performance.
Reduced sensor-motor coupling correlates with decreased group effectiveness.
Abstract
This study investigates collective behaviors that emerge from a group of homogeneous individuals optimized for a specific capability. We created a group of simple, identical neural network based agents modeled after chemotaxis-driven vehicles that follow pheromone trails and examined multi-agent simulations using clones of these evolved individuals. Our results show that the evolution of individuals led to population differentiation. Surprisingly, we observed that collective fitness significantly changed during later evolutionary stages, despite maintained high individual performance and simplified neural architectures. This decline occurred when agents developed reduced sensor-motor coupling, suggesting that over-optimization of individual agents almost always lead to less effective group behavior. Our research investigates how individual differentiation can evolve through what…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsEvolutionary Algorithms and Applications · Reinforcement Learning in Robotics
