SwarmRL: building the future of smart active systems
Open Access
- 7 April 2025
- journal article
- tips and-tricks---soft-matter
- Published by Springer Nature in The European Physical Journal E
- Vol. 48 (4-5) , 1-13
Abstract
This work introduces , a Python package designed to study intelligent active particles. provides an easy-to-use interface for developing models to control microscopic colloids using classical control and deep reinforcement learning approaches. These models may be deployed in simulations or real-world environments under a common framework. We explain the structure of the software and its key features and demonstrate how it can be used to accelerate research. With , we aim to streamline research into micro-robotic control while bridging the gap between experimental and simulation-driven sciences. is available open-source on GitHub at https://github.com/SwarmRL/SwarmRL.Keywords
All Related Versions
Funding Information
- Deutsche Forschungsgemeinschaft (2075-390740016, 497249646, 327154368, INST 35/1597-1 FUGG)
- Deutsche Forschungsgemeinschaft (492175459)
This publication has 64 references indexed in Scilit:
- Magnetically driven microrobots: Recent progress and future developmentMaterials & Design, 2023
- Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms2021
- Janus particles: design, preparation, and biomedical applicationsMaterials Today Bio, 2019
- MOFBOTS: Metal–Organic‐Framework‐Based Biomedical MicrorobotsAdvanced Materials, 2019
- Bioengineered and biohybrid bacteria-based systems for drug deliveryAdvanced Drug Delivery Reviews, 2016
- Multiagent Systems Under Uncertainty2016
- Biocompatible, accurate, and fully autonomous: a sperm-driven micro-bio-robotJournal of Micro and Bio Robotics, 2014
- Search and Rescue Robotics2008
- Markov games as a framework for multi-agent reinforcement learning1994
- Multi-Agent Reinforcement Learning: Independent vs. Cooperative Agents1993