Separating Decision Time from Decision Quality in the Real-Time Gap of Distilled Deciders: Evidence from a Game and a Conveyor Simulator

Excerpt

arXiv:2610.04810v1 Announce Type: cross Abstract: Real-time agents are often evaluated with the world paused, or with decision time rounded to whole ticks (tick conversion). Tick conversion predicts almost no loss for a learned decider whose hit accuracy falls by 14.8 percentage points (pp) on the same games in asynchronous play. We instead split the decider's gap to a zero-latency teacher into time and quality components. In ViZDoom, we train a small decider by imitating a scripted teacher, run