Doctoral Project: Learning of intelligent swarm behavior
Part of research project: Learning of intelligent swarm behavior
Description of the research project
This project aims at understanding and learning collective intelligent behavior using a combination of behavioral biology, phenomenological swarm modelling and multi-agent reinforcement learning.
Description of the doctoral project
This subproject will develop methods for the optimization of collective behavior in groups of agents that mimic animal groups and swarms. These methods will be applied to learn and study collective behavior in robotic agents, and used to develop an understanding of observed behavior in real animal groups. The project involves a close collaboration between researchers in behavioral biology and machine learning, and will primarily be supervised by H. Sprekeler, in close interaction with P. Romanczuk and D. Bierbach.
Project start date: October 1, 2019 (an earlier starting date may be possible)
Applicants must hold a Diploma/Master’s degree in a highly quantitative field (e.g., mathematics, physics, computer science, engineering). The applicant should have
• excellent mathematical skills
• excellent programming skills (e.g., Python, Matlab, C)
• very good command of English, both written and spoken, and
• a keen interest in understanding intelligence and the strong communicative skills required for interdisciplinary research.
The ideal candidate has a background in machine learning, with expertise in (multi-agent) reinforcement learning.