Evolution of Collective AI Beyond Individual Optimization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913595364737024 |
|---|---|
| author | Takata, Ryosuke Tang, Yujin Tian, Yingtao Maruyama, Norihiro Kojima, Hiroki Ikegami, Takashi |
| author_facet | Takata, Ryosuke Tang, Yujin Tian, Yingtao Maruyama, Norihiro Kojima, Hiroki Ikegami, Takashi |
| contents | 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 evolutionary pathways. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_02085 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evolution of Collective AI Beyond Individual Optimization Takata, Ryosuke Tang, Yujin Tian, Yingtao Maruyama, Norihiro Kojima, Hiroki Ikegami, Takashi Multiagent Systems Artificial Intelligence 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 evolutionary pathways. |
| title | Evolution of Collective AI Beyond Individual Optimization |
| topic | Multiagent Systems Artificial Intelligence |
| url | https://arxiv.org/abs/2412.02085 |