A Study of AI Population Dynamics with Million-agent Reinforcement Learning

TL;DR

This paper empirically investigates the collective dynamics of a large population of AI agents using million-agent reinforcement learning in a simulated predator-prey environment, revealing ordered patterns and emergent behaviors akin to natural population models.

Contribution

It introduces a large-scale DRL platform for simulating millions of agents and demonstrates that their population dynamics follow natural laws like the Lotka-Volterra model.

Findings

Population dynamics resemble Lotka-Volterra patterns.

Emergent group behaviors depend on environmental resources.

Self-organization explains collective adaptation behaviors.

Abstract

We conduct an empirical study on discovering the ordered collective dynamics obtained by a population of intelligence agents, driven by million-agent reinforcement learning. Our intention is to put intelligent agents into a simulated natural context and verify if the principles developed in the real world could also be used in understanding an artificially-created intelligent population. To achieve this, we simulate a large-scale predator-prey world, where the laws of the world are designed by only the findings or logical equivalence that have been discovered in nature. We endow the agents with the intelligence based on deep reinforcement learning (DRL). In order to scale the population size up to millions agents, a large-scale DRL training platform with redesigned experience buffer is proposed. Our results show that the population dynamics of AI agents, driven only by each agent's individual self-interest, reveals an ordered pattern that is similar to the Lotka-Volterra model studied in population biology. We further discover the emergent behaviors of collective adaptations in studying how the agents' grouping behaviors will change with the environmental resources. Both of the two findings could be explained by the self-organization theory in nature.