portfolioUser's headshot

MARL

Multi-Agent Reinforcement Learning (MARL) is a subfield of artificial intelligence that combines multi-agent systems and reinforcement learning. It is concerned with the study of how multiple agents can learn to interact with each other in a shared environment to achieve their goals.

MAS Emergence Safety
MAS Emergence Safety

Formalized MAS emergence misalignment; proposed safety mitigation strategies.

Aquarium MARL Environment
Aquarium MARL Environment

Aquarium: Open-source MARL environment for predator-prey studies.

AI-Fusion Safety
AI-Fusion Safety

Studied MARL emergence and safety, built simulations with Fraunhofer.