Author

Michael Levin

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Conference Open access Aug 2026

The Informationally Integrated Alignment Hypothesis: Integrated Information Aligns with and Predicts Final Reward in Reinforcement Learning Agents

This work focused on Reinforcement Learning of neural-network agents across a range of environmental conditions, encompassing different algorithms, agent architectures, and six environments arranged along a complexity spectrum and suggested a Causally Emergent Alignment Hypothesis: successful agents exhibited integrate...

F. Pigozzi, Michael Levin · IEEE Symposium on Artificial... · 0 citations

#machine learning Preprint Sep 2026

On Growth and Form, and Function: Reusable Regulatory Handles Control Phenotypic Variation

The results provide a computational realization of D'Arcy Thompson's remarkable grid transformations in a 2D NCA---a minimal cybernetic tissue in which variations of fully grown emoji phenotypes can be encoded, combined, and controlled through low-dimensional directions in regulatory weight space.

Benedikt Hartl, Milton L. Montero, Marcello Barylli et al. · 0 citations

#artificial intelligence Conference Open access Jun 2026

The Artificial Experimentalist: Discovery and Control of Self-Organizing Phenomena with Autotelic Reinforcement Learning

A closed-loop framework based on autotelic reinforcement learning is introduced, in which an agent autonomously samples diverse goals and learns a goal-conditioned policy to intervene in a complex system through minimal, local perturbations, suggesting a path toward artificial experimentalist agents that, autonomously...

Marko Cvjetko, Benedikt Hartl, Michael Levin et al. · IEEE Symposium on Artificial... · 0 citations