Book
An up-to-date, unified and rigorous treatment of theoretical, computational and applied research on Markov decision process models. Concentrates on infinite-horizon discrete-time models. Discusses arbitrary state spaces, finite-horizon and continuous-time discrete-state models. Also covers modified policy iteration, multichain models with average reward criterion and sensitive optimality. Features a wealth of figures which illustrate examples and an extensive bibliography. «
Boeklezers.nl is a network for social reading. We help readers discover new books and authors, and bring readers in contact with each other and with writers. Read more ».
Nobody