SwarmRL: Building the Future of Smart Active Systems

1 code implementation • 25 Apr 2024 • Samuel Tovey, Christoph Lohrmann, Tobias Merkt, David Zimmer, Konstantin Nikolaou, Simon Koppenhöfer, Anna Bushmakina, Jonas Scheunemann, Christian Holm

This work introduces SwarmRL, a Python package designed to study intelligent active particles.

Emergence of Chemotactic Strategies with Multi-Agent Reinforcement Learning

no code implementations • 2 Apr 2024 • Samuel Tovey, Christoph Lohrmann, Christian Holm

We study the efficiency of the emergent policy and identify convergence in agent size and swim speeds.

Multi-agent Reinforcement Learning reinforcement-learning +1

ZnTrack -- Data as Code

1 code implementation • 19 Jan 2024 • Fabian Zills, Moritz Schäfer, Samuel Tovey, Johannes Kästner, Christian Holm

The past decade has seen tremendous breakthroughs in computation and there is no indication that this will slow any time soon.

Management

Environmental effects on emergent strategy in micro-scale multi-agent reinforcement learning

1 code implementation • 3 Jul 2023 • Samuel Tovey, David Zimmer, Christoph Lohrmann, Tobias Merkt, Simon Koppenhoefer, Veit-Lorenz Heuthe, Clemens Bechinger, Christian Holm

Multi-Agent Reinforcement Learning (MARL) is a promising candidate for realizing efficient control of microscopic particles, of which micro-robots are a subset.

Multi-agent Reinforcement Learning reinforcement-learning +1

Towards a Phenomenological Understanding of Neural Networks: Data

no code implementations • 1 May 2023 • Samuel Tovey, Sven Krippendorf, Konstantin Nikolaou, Christian Holm

This framework is then applied to the problem of optimal data selection for the training of NNs.