tailieunhanh - Optimal Learning

This book emerged from a stream of research conducted in CASTLE Laboratory at Princeton University during the period 2006 - 2011. Initially, the work was motivated by the "exploration vs. exploitation" problem that arises in the design of algorithms for approximate dynamic programming, where it may be necessary to visit a state to learn the value of being in the state. However, we quickly became aware that this basic question had many applications outside of dynamic programming. The results of this research were made possible by the efforts and contributions of numerous colleagues. The work was conducted under the guidance and supervision of Warren Powell, founder and director. | Warren B. Powell Ilya 0. Ryzhov Optimal Learning WILEY SERIES IN PROBABILITY AND STATISTICS Established by WALTER A. SHEWHART and SAMUEL S. WILKS Editors David J. Balding Noel A. c. Cressie Garrett M. Fitzmaurice Harvey Goldstein Iain M. Johnstone Geert Molenberghs David w. Scott Adrian F. M. Smith Ruey s. Tsay Sanford Weisberg Editors Emeriti Vic Barnett J. Stuart Hunter Joseph B. Kadane Jozef L. Teugels A complete list of the titles in this series appears at the end of this .