We identify a new "order parameter" for the disorder-driven many-body localization transition by leveraging machine learning. Contrary to previous studies, our method is almost entirely unsupervised. A game theoretic process between neural networks defines an adversarial setup with conflicting objectives to identify what characteristic features to base efficient predictions on. This reduces the numerical effort for mapping out the phase diagram by a factor of 100 × and allows us to pin down the transition, as the point at which the physics changes qualitatively, in an objective and cleaner way than is possible with the existing diverse array of quantities. Our approach of automated discovery is applicable specifically to poorly understood phase transitions and is a starting point for a research program leveraging the potential of machine learning-assisted research in physics.