One-armed bandit models with continuous and delayed responses

DOI10.1007/s001860300295zbMath1037.93078OpenAlexW2024490033MaRDI QIDQ1416785

Xikui Wang, Mikelis G. Bickis

Publication date: 16 December 2003

Published in: Mathematical Methods of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s001860300295

zbMATH Keywords

Markov decision processesoptimal stoppingGittins indexbandit processesdelayed responses

Mathematics Subject Classification ID

Optimal stochastic control (93E20) Stopping times; optimal stopping problems; gambling theory (60G40) Markov and semi-Markov decision processes (90C40)

Related Items (4)

One-armed bandit process with a covariate ⋮ Clinical Trials with Exponential Survival Times ⋮ INDEXABILITY OF BANDIT PROBLEMS WITH RESPONSE DELAYS ⋮ Optimal investment and consumption with stochastic dividends

This page was built for publication: One-armed bandit models with continuous and delayed responses