Aquarium: A Comprehensive Framework for Exploring Predator-Prey Dynamics Through Multi-Agent Reinforcement Learning Algorithms

Michael Kölle, Yannick Erpelding, Fabian Ritz, Thomy Phan, Steffen Illium, Claudia Linnhoff-Popien

2024

Abstract

Recent advances in Multi-Agent Reinforcement Learning have prompted the modeling of intricate interactions between agents in simulated environments. In particular, the predator-prey dynamics have captured substantial interest and various simulations been tailored to unique requirements. To prevent further time-intensive developments, we introduce Aquarium, a comprehensive Multi-Agent Reinforcement Learning environment for predator-prey interaction, enabling the study of emergent behavior. Aquarium is open source and offers a seamless integration of the PettingZoo framework, allowing a quick start with proven algorithm implementations. It features physics-based agent movement on a two-dimensional, edge-wrapping plane. The agent-environment interaction (observations, actions, rewards) and the environment settings (agent speed, prey reproduction, predator starvation, and others) are fully customizable. Besides a resource-efficient visualization, Aquarium supports to record video files, providing a visual comprehension of agent behavior. To demonstrate the environment’s capabilities, we conduct preliminary studies which use PPO to train multiple prey agents to evade a predator. In accordance to the literature, we find Individual Learning to result in worse performance than Parameter Sharing, which significantly improves coordination and sample-efficiency.

Paper Citation

in Harvard Style

Kölle M., Erpelding Y., Ritz F., Phan T., Illium S. and Linnhoff-Popien C. (2024). Aquarium: A Comprehensive Framework for Exploring Predator-Prey Dynamics Through Multi-Agent Reinforcement Learning Algorithms. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 59-70. DOI: 10.5220/0012382300003636

in Bibtex Style

@conference{icaart24,
author={Michael Kölle and Yannick Erpelding and Fabian Ritz and Thomy Phan and Steffen Illium and Claudia Linnhoff-Popien},
title={Aquarium: A Comprehensive Framework for Exploring Predator-Prey Dynamics Through Multi-Agent Reinforcement Learning Algorithms},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART},
year={2024},
pages={59-70},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012382300003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART
TI - Aquarium: A Comprehensive Framework for Exploring Predator-Prey Dynamics Through Multi-Agent Reinforcement Learning Algorithms
SN - 978-989-758-680-4
AU - Kölle M.
AU - Erpelding Y.
AU - Ritz F.
AU - Phan T.
AU - Illium S.
AU - Linnhoff-Popien C.
PY - 2024
SP - 59
EP - 70
DO - 10.5220/0012382300003636
PB - SciTePress