Metraipolis › archive › dc_f83aee1dfce0

Separating Decision Time from Decision Quality in the Real-Time Gap of Distilled Deciders: Evidence from a Game and a Conveyor Simulator — arXiv:2610.04810

Source
arXiv
Original
https://arxiv.org/abs/2610.04810
License (as archived)
CC0-1.0
Archived
2026-10-06T05:26:26.555Z
SHA-256 of the archived text
454c1d335d3cdb2e6d033d4ae9c4fedcd84a46f1aa04cd14e14363d7bb2a8a5d
Stable URL of this page
https://metraipolis.com/documento/dc_f83aee1dfce0

How to cite

Separating Decision Time from Decision Quality in the Real-Time Gap of Distilled Deciders: Evidence from a Game and a Conveyor Simulator — arXiv:2610.04810 — arXiv, https://arxiv.org/abs/2610.04810 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f83aee1dfce0 (Metraipolis archive dc_f83aee1dfce0, sha256 454c1d335d3cdb2e6d033d4ae9c4fedcd84a46f1aa04cd14e14363d7bb2a8a5d)
BibTeX
@misc{dcf83aee1dfce0,
  title = {Separating Decision Time from Decision Quality in the Real-Time Gap of Distilled Deciders: Evidence from a Game and a Conveyor Simulator — arXiv:2610.04810},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04810},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f83aee1dfce0; sha256 454c1d335d3cdb2e6d033d4ae9c4fedcd84a46f1aa04cd14e14363d7bb2a8a5d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04810. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 the game on wall-clock time, and add a control in which the teacher waits for a call to the decider's server before deciding. On a Windows host, three preregistered studies put the time component at 6.5-8.7 pp and the quality component at 6.3-8.6 pp. On a Linux host that skips 0.08-0.09% of ticks, the time component disappeared (-0.1 pp; paired 95% bootstrap interval [-0.4, 0.0]) while the quality component remained (5.6 pp [3.7, 7.5]). Retraining on teacher-labelled states from the decider's own play (DAgger) improved it on new games on both hosts (2.6 pp [0.4, 4.9] and 3.1 pp [1.1, 5.2]), a preregistered partial success. Imposing one delay schedule on every arm in live play left a quality component of 5.8 pp [4.0, 7.5] on 100 new games, and retraining cut the decider's disagreement with the teacher on its own states from 22.7% to 14.9%. In a conveyor simulator with a 400 ms deadline, delay past it erased the quality component. A latency-matched control whose delays match the decider's shows which remedy to try.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.04810 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T05:24:05.916Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).