Throughout this work, we investigate if diversity across neural activations ( 2) reflects model generalizability.

Federated learning (FL) is a machine learning paradigm where multiple client devices train models collaboratively without data exchange.

These embodied agents are typically trainedtabula rasain isolated worlds with limited complexity and diversity. Although highly performant, theyare specialist models that do not generalize beyond a narrowsetoftasks.

By making our data processing source code publiclyavailable, weaim toengage themarine science community toenrich thedata pool andinspire themachine learning community to develop more robust models.