Deep active inference agents using Monte-Carlo methods

Active Inference just got real, thanks to Monte Carlo trees and information theory.

Causal blankets: Theory and algorithmic framework

Like Markov blankets, but that actually do what you think they do.

Learning, compression, and leakage: Minimizing classification error via meta-universal compression principles

Connections between information theory, supervised learning, and privacy

Relational forward models for multi-agent learning

Using graph neural networks to understand and improve multi-agent RL.