Active Inference with a Self-Prior in the Mirror-Mark Task

TL;DR

This paper presents a computational model using active inference and a self-prior to simulate mirror self-recognition behavior, demonstrating spontaneous self-awareness without external rewards.

Contribution

It introduces a novel Transformer-based self-prior mechanism that explains mirror self-recognition as emerging from multisensory experience learning, without explicit training.

Findings

Simulated infant recognized and removed a face sticker in 70% of cases.

Self-prior acts as an internal criterion for self versus non-self.

Model captures visual-proprioceptive associations as a probabilistic body schema.

Abstract

The mirror self-recognition test evaluates whether a subject touches a mark on its own body that is visible only in a mirror, and is widely used as an indicator of self-awareness. In this study, we present a computational model in which this behavior emerges spontaneously through a single mechanism, the self-prior, without any external reward. The self-prior, implemented with a Transformer, learns the density of familiar multisensory experiences; when a novel mark appears, the discrepancy from this learned distribution drives mark-directed behavior through active inference. A simulated infant, relying solely on vision and proprioception without tactile input, discovered a sticker placed on its own face in the mirror and removed it in approximately 70% of cases without any explicit instruction. Expected free energy decreased significantly after sticker removal, confirming that the self-prior operates as an internal criterion for distinguishing self from non-self. Cross-modal sampling further demonstrated that the self-prior captures visual--proprioceptive associations, functioning as a probabilistic body schema. These results provide a concise computational account of the key behavior observed in the mirror test and suggest that the free energy principle can serve as a unifying hypothesis for investigating the developmental origins of self-awareness. Code is available at: https://github.com/kim135797531/self-prior-mirror