Yunus Emre Demirci, Somnath Pradhan, Serdar Yüksel · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28377 · open-access PDF
Kami mempelajari masalah kontrol stokastik berkelanjutan-waktu di bawah informasi parsial. kontribusi utama kami adalah sebagai berikut: (i) Kami menunjukkan hampir optimalitas, di bawah cakrawala terbatas serta kriteria biaya cakrawala tak terbatas diskon, dari kebijakan kontrol konstan yang diperoleh melalui solusi untuk pendekatan proses keputusan Markov (POMDP) yang dapat diamati parsial-waktu, yang dibangun melalui pendekatan Euler-Maruyama dari kedua negara dan proses observasi; (ii) kami mendapatkan beberapa sifat regularitas dari model POMDP tersebut; dan (iii) menggunakan sifat regularitas ini, kami mencapai n
Machine translation (Meta M2M100); the English original follows.
We study continuous-time stochastic control problems under partial information. Our main contributions are the following: (i) We show near optimality, under finite horizon as well as discounted infinite horizon cost criteria, of piece-wise constant control policies obtained via solutions to discrete-time partially observable Markov decision process (POMDP) approximations, constructed via Euler-Maruyama approximations of both state and observation processes; (ii) we obtain several regularity properties of such POMDP approximate models; and (iii) using these regularity properties, we arrive at n
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28377, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange