Asymptotically efficient adaptive allocation schemes for controlled i.i.d. processes: finite parameter space
From MaRDI portal
Publication:3818930
DOI10.1109/9.16415zbMath0666.93077MaRDI 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
Related Items
Unnamed Item, Learning the distribution with largest mean: two bandit frameworks, Learning to Optimize via Information-Directed Sampling, Matching While Learning, Unnamed Item, Bounded Regret for Finitely Parameterized Multi-Armed Bandits, Certainty equivalence control with forcing: Revisited, Strong consistency of Bayes estimates in nonlinear stochastic regression models, Open problems in universal induction \& intelligence, Asymptotically efficient strategies for a stochastic scheduling problem with order constraints., Optimal strategies for a class of sequential control problems with precedence relations, Arbitrary side observations in bandit problems