website/_posts/projects/2020-05-01-FIKS.md

layout, title, categories, tags, excerpt, header, role, skills

layout	title	categories	tags	excerpt	header	role	skills
single	AI-Fusion Safety	projects	multi-agent-systems reinforcement-learning safety emergence simulation	Studied MARL emergence and safety, built simulations with Fraunhofer.	teaser /assets/images/projects/robot.png	Researcher, Software Developer	Multi-Agent Reinforcement Learning (MARL), Emergence Analysis, AI Safety, Simulation Environment Design, Python, Gymnasium API, Software Engineering, Unity (Visualization), Industry Collaboration

Project Resources

• GitHub Repo
• Install via PyPI
• ReadTheDocs
• {% cite altmann2024emergence %}

{: style="margin:0em; padding:0em; width:15em"}

{: .align-left style="padding:0.1em; width:5em"} Project: AI-Fusion
Partner: Fraunhofer Institute for Cognitive Systems (IKS)
Duration: 2022 - 2023
Objective: To investigate the detection and mitigation of potentially unsafe emergent behaviors in complex systems composed of multiple interacting AI agents, particularly in scenarios involving heterogeneous agents (e.g., mixed-vendor autonomous systems).

In collaboration with Fraunhofer IKS, the AI-Fusion project addressed the critical challenge of understanding and ensuring safety in multi-agent reinforcement learning (MARL) systems. Emergence, defined as the arising of complex, often unpredictable, system-level dynamics from local interactions between agents and their environment, was a central focus due to its implications for system safety and reliability.

---

To facilitate research into these phenomena, key contributions included the development of specialized simulation tools:

1. High-Performance MARL Simulation Environment:

• A flexible and efficient simulation environment was developed in Python, adhering to the Gymnasium (formerly Gym) API specification.
• Purpose: Designed specifically for training and evaluating reinforcement learning algorithms in multi-agent contexts prone to emergent behaviors.
• Features:
  • Modularity: Supports diverse scenarios through configurable modules and configurations.
  • Observation/Action Spaces: Handles complex agent interactions, including per-agent observations and sequential/multi-agent action coordination.
  • Performance: Optimized for efficient simulation runs, enabling extensive experimentation.

2. Unity-Based Demonstrator Unit:

• A complementary visualization tool was created using the Unity engine.
• Purpose: Allows for the replay, inspection, and detailed analysis of specific simulation scenarios and agent interactions.
• Utility: Aids researchers in identifying and understanding the mechanisms behind observed emergent dynamics.
• View Demonstrator on GitHub

Conceptual relationship defining emergence in multi-agent systems.

This project involved close collaboration with industry-focused researchers, software development adhering to modern standards, and deep investigation into the theoretical underpinnings of emergence and safety in MARL systems. The developed tools provide a valuable platform for continued research in this critical area.

{% include reference.html %}