On the optimal solution of the one-armed bandit adaptive control problem
DOI10.1109/TAC.1981.1102790zbMath0475.90087OpenAlexW2164360744MaRDI QIDQ3931046
P. R. Kumar, Thomas I. Seidman
Publication date: 1981
Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1109/tac.1981.1102790
optimal strategyoptimal solutionsequential design of experimentsdesigns for clinical trialsgood approximations to boundary functionone-armed bandit adaptive control problemsequential adaptive controltwo slot machines
Bayesian problems; characterization of Bayes procedures (62C10) Optimal stochastic control (93E20) Stopping times; optimal stopping problems; gambling theory (60G40) Markov and semi-Markov decision processes (90C40) Sequential statistical design (62L05)
Related Items