Course details


Emergent Behaviors in a Multi-Agent System with Reinforcement Learning

WS 2022 Dr. Elia Bruni, Julius Mayer OFFLINE
M.Sc modules:
CC-MP-SP - Study Project
CS-MP-SP - Study Project
Tue: 15-18
Thu: 15-18

In this study project, the group will work together to develop a multi-agent system to simulate a microcosm of simple artificial organisms in a standard foraging scenario, trained with reinforcement learning. Emergent properties and dynamics between populations of agents, e.g. language, cooperation, and group strategies can be further explored and selected as research objectives. Prerequisites are competence in programming and either basic experience with simulation frameworks such as Unity or MuJoCo or basic knowledge of ML / RL.