#machine learning
May 2026
Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning
This work introduces a framework that decouples agent identity from behavior, capturing a continuous manifold from which agents instantiate their behaviors in response to events, and proves that this construction ensures that diversity does not interfere with reward maximization by design.
Hannes Büchi, Manon Flageat, Eduardo Sebastián et al.
· arXiv.org · 1 citation