Herein we review certain problems in sequential optimization when the underlying dynamical system is not fully specified but has to be learned during the operation of the system. A prototypical example is the multi-armed bandit problem, which was one of Yakowitz’s many research areas. Other problems under review include stochastic approximation and adaptive control of Markov chains.
CITATION STYLE
Lai, T. L. (2016). Sequential optimization under uncertainty. In International Series in Operations Research and Management Science (Vol. 46, pp. 35–55). Springer New York LLC. https://doi.org/10.1007/0-306-48102-2_3
Mendeley helps you to discover research relevant for your work.