Metraipolis › archive › dc_0c43bd3b60f1
Quantile Propagation Planning for Budgeted Tail-Risk Evaluation — arXiv:2610.41351
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41351
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-02T07:50:45.343Z
- SHA-256 of the archived text
32e09cdcd0c8fc3895e6b33a039cb7976c4375b81f78411a8785077992558f02- Stable URL of this page
https://metraipolis.com/documento/dc_0c43bd3b60f1
How to cite
Quantile Propagation Planning for Budgeted Tail-Risk Evaluation — arXiv:2610.41351 — arXiv (en), https://arxiv.org/abs/2610.41351 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0c43bd3b60f1 (Metraipolis archive dc_0c43bd3b60f1, sha256 32e09cdcd0c8fc3895e6b33a039cb7976c4375b81f78411a8785077992558f02)
BibTeX
@misc{dc0c43bd3b60f1,
title = {Quantile Propagation Planning for Budgeted Tail-Risk Evaluation — arXiv:2610.41351},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41351},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0c43bd3b60f1; sha256 32e09cdcd0c8fc3895e6b33a039cb7976c4375b81f78411a8785077992558f02},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41351. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Risk-aware planning must identify rare, costly outcomes using only a limited number of model evaluations. Monte Carlo rollouts spend this budget on noisy tail estimates, while planning from the mean can miss the tail entirely. We introduce quantile propagation planning (QPP), which propagates a small, fixed set of disturbance quantiles through the dynamics and integrates the resulting cost curve to evaluate both mean and tail risk. The method is exact at the propagated levels, converges as the quantile grid is refined, and admits a one-sided conservatism guarantee under stated structural conditions. In controlled overload and inventory tasks, QPP reduces realized tail cost and constraint violations relative to mean-rollout planning. On overload, it remains competitive with sampled evaluators that use substantially more trajectories. These results position QPP as a transparent, budget-controlled approach to tail-risk evaluation. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2610.41351 — 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 2026-11-02T07:40:00.185Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).