A Study Of AI Population Dynamics With Million-agent Reinforcement Learning

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

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyang2017a

Related papers

• The Evolutionary Dynamics Of Independent Learning Agents In Population Games (2020)0.00
• A Survey On Large-population Systems And Scalable Multi-agent Reinforcement Learning (2022)0.00
• Evolution Of Societies Via Reinforcement Learning (2024)0.00
• Evolutionary Multi-agent Reinforcement Learning In Group Social Dilemmas (2024)0.00
• Genai-based Multi-agent Reinforcement Learning Towards Distributed Agent Intelligence: A Generative-rl Agent Perspective (2025)0.00
• Dynamics Of Moral Behavior In Heterogeneous Populations Of Learning Agents (2024)4.52
• Inclusive Fitness As A Key Step Towards More Advanced Social Behaviors In Multi-agent Reinforcement Learning Settings (2025)0.00
• Magent: A Many-agent Reinforcement Learning Platform For Artificial Collective Intelligence (2017)0.00