Metraipolis › archive › dc_473971e8a336
Data-Driven Brownian Reflection Control — arXiv:2609.03870
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03870
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T02:26:49.673Z
- SHA-256 of the archived text
6b073b574da634bd6a09c0fab19179f5f21f40617fd20095c129fa1eeff7f0c4- Stable URL of this page
https://metraipolis.com/documento/dc_473971e8a336
How to cite
Data-Driven Brownian Reflection Control — arXiv:2609.03870 — arXiv (en), https://arxiv.org/abs/2609.03870 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_473971e8a336 (Metraipolis archive dc_473971e8a336, sha256 6b073b574da634bd6a09c0fab19179f5f21f40617fd20095c129fa1eeff7f0c4)
BibTeX
@misc{dc473971e8a336,
title = {Data-Driven Brownian Reflection Control — arXiv:2609.03870},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03870},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_473971e8a336; sha256 6b073b574da634bd6a09c0fab19179f5f21f40617fd20095c129fa1eeff7f0c4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03870. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study a data-driven reflection control problem for a Brownian model with unknown drift and volatility. We first propose a learn-then-optimize (LTO) algorithm: it estimates the policy-relevant parameter during exploration, plugs the estimate into the optimality equation, and exploits the resulting policy---achieving an $O(\sqrt{T})$ finite-time expected regret bound. We further propose two algorithms, adaptive-updating (AU) and full-history adaptive-updating (AU-FH), which continuously update the estimator and reflecting level, attaining an improved $O(\log T)$ regret bound. Notably, AU-FH algorithms leverages all historical data, yielding better performance in numerical simulations. Our analysis decomposes regret into exploration, transient, and learning components. Transient regret from nonstationarity is bounded by the time-integrated deviation of the transition semigroup from stationarity evaluated on the holding cost, which can be further bounded via a Foster-Lyapunov inequality for exponential convergence of the controlled reflected Brownian motion (RBM). For learning regret, we establish local regularity properties together with consistency and mean-squared error bounds for the estimator, which control the stationary cost gap between the learned and optimal reflection policies. In addition, we leverage the monotonicity of the moving boundary Skorokhod map to derive moment bounds for the AU algorithms' switching states, via pathwise comparison with fixed-boundary RBMs.
Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-04 in math.OC).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.03870 — 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 2026-10-17T02:07:43.344Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).