SwarmRL: Building the Future of Smart Active Systems

Samuel Tovey, Christoph Lohrmann, Tobias Merkt, David Zimmer, Konstantin Nikolaou +4 more
4/25/2024
cs.ROcond-mat.softcs.AI

Official code: SwarmRL/SwarmRL (44 stars, EPL-2.0, JAX, last commit 2026-03-28).

Abstract

This work introduces SwarmRL, a Python package designed to study intelligent active particles. SwarmRL 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 SwarmRL, we aim to streamline research into micro-robotic control while bridging the gap between experimental and simulation-driven sciences. SwarmRL is available open-source on GitHub at https://github.com/SwarmRL/SwarmRL.

View on arXivView PDF

Code Implementations(1)

SwarmRL/SwarmRLOfficial100%
JAXEPL-2.0

Multi agent reinforcement learning for intelligent active matter

4410C++, CMakeMar 8, 20236 months agoEPL-2.0
active-matterespressomdjaxmicrorobotsreinforcement-learning

Similar Papers

MEMTRACK: A Deep Learning-Based Approach to Microrobot Tracking in Dense and Low-Contrast Environments

79% match1 repo12023

DRIFT: Deep Reinforcement Learning for Intelligent Floating Platforms Trajectories

79% match1 repo402023

Simulation of Nanorobots with Artificial Intelligence and Reinforcement Learning for Advanced Cancer Cell Detection and Tracking

78% match2024

Chemotaxis of sea urchin sperm cells through deep reinforcement learning

78% match2022

Learning to Simulate Complex Physics with Graph Networks

78% match1 repo15.2k2020

EINCASM: Emergent Intelligence in Neural Cellular Automaton Slime Molds

78% match2023

Cite this paper

@article{tovey2024swarmrl,
  title  = {SwarmRL: Building the Future of Smart Active Systems},
  author = {Samuel Tovey and Christoph Lohrmann and Tobias Merkt and David Zimmer and Konstantin Nikolaou and Simon Koppenhöfer and Anna Bushmakina and Jonas Scheunemann and Christian Holm},
  year   = {2024},
  eprint = {2404.16388},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2404.16388v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2404.16388.svg)](https://codeofpaper.com/paper/2404.16388)

Discussion