UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

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

Yang, Y; Wen, Y; Yu, L; Zhang, W; Bai, Y; Wang, J; (2018) A Study of AI Population Dynamics with Million-agent Reinforcement Learning. In: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems. (pp. pp. 2133-2135). ACM Green open access

[thumbnail of Wang_A study of AI population dynamics with million-agent reinforcement learning_AAM.pdf]
Preview
Text
Wang_A study of AI population dynamics with million-agent reinforcement learning_AAM.pdf - Accepted version

Download (5MB) | Preview

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.

Type: Proceedings paper
Title: A Study of AI Population Dynamics with Million-agent Reinforcement Learning
Event: AAMAS '18 Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems
Location: Stockholm, Sweden
Dates: 10th-15th July 2018
Open access status: An open access version is available from UCL Discovery
Publisher version: https://dl.acm.org/citation.cfm?id=3238096
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Multi-agent reinforcement learning, population dynamics
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > UCL School of Management
URI: https://discovery.ucl.ac.uk/id/eprint/10066101
Downloads since deposit
71Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item