Asymptotically efficient adaptive allocation schemes for controlled i.i.d. processes: finite parameter space

DOI10.1109/9.16415zbMath0666.93077OpenAlexW2013532620MaRDI QIDQ3818930

Rajeev Agrawal, V. Anantharam, Demosthenis Teneketzis

Publication date: 1989

Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1109/9.16415

zbMATH Keywords

infinite horizon

Mathematics Subject Classification ID

Adaptive control/observation systems (93C40) Optimal stochastic control (93E20)

Related Items (12)

Bounded Regret for Finitely Parameterized Multi-Armed Bandits ⋮ Open problems in universal induction \& intelligence ⋮ Learning the distribution with largest mean: two bandit frameworks ⋮ Optimal strategies for a class of sequential control problems with precedence relations ⋮ Arbitrary side observations in bandit problems ⋮ Unnamed Item ⋮ Learning to Optimize via Information-Directed Sampling ⋮ Certainty equivalence control with forcing: Revisited ⋮ Matching While Learning ⋮ Strong consistency of Bayes estimates in nonlinear stochastic regression models ⋮ Asymptotically efficient strategies for a stochastic scheduling problem with order constraints. ⋮ Unnamed Item

This page was built for publication: Asymptotically efficient adaptive allocation schemes for controlled i.i.d. processes: finite parameter space