Asymptotically efficient adaptive allocation schemes for controlled Markov chains: finite parameter space
From MaRDI portal
Publication:3032153
DOI10.1109/9.40770zbMath0689.93039OpenAlexW2158049833MaRDI QIDQ3032153
Demosthenis Teneketzis, Rajeev Agrawal, V. Anantharam
Publication date: 1989
Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1109/9.40770
infinite horizonasymptotically efficientcontrolled Markov chainuniformly good adaptive control schemes
Adaptive control/observation systems (93C40) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Stochastic systems in control theory (general) (93E03)
Related Items (8)
Open problems in universal induction \& intelligence ⋮ The multi-armed bandit problem: an efficient nonparametric solution ⋮ Optimal strategies for a class of sequential control problems with precedence relations ⋮ Arbitrary side observations in bandit problems ⋮ Computing Optimal Policies for Markovian Decision Processes Using Simulation ⋮ Learning to Optimize via Information-Directed Sampling ⋮ Certainty equivalence control with forcing: Revisited ⋮ Strong consistency of Bayes estimates in nonlinear stochastic regression models
This page was built for publication: Asymptotically efficient adaptive allocation schemes for controlled Markov chains: finite parameter space
