Saved in:
Bibliographic Details
Main Author: Pae, Hongju
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.02902
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • This study operationalizes subjective perspective in artificial agents by grounding it in a minimal, phenomenologically motivated internal structure. The perspective is implemented as a slowly evolving global latent state that modulates fast policy dynamics without being directly optimized for behavioral consequences. In a reward-free environment with regime shifts, this latent structure exhibits direction-dependent hysteresis, while policy-level behavior remains comparatively reactive. I argue that such hysteresis constitutes a measurable signature of perspective-like subjectivity in machine systems.