Sold by Mighty Ape
This book is devoted to a unified treatment of Competitive Markov Decision Processes. It examines these processes from the standpoints of modeling and of optimization, providing newcomers to the field with an accessible account of algorithms, theory, and applications, while also supplying specialists with a comprehensive survey of recent developments. The treatment is self-contained, requiring only some knowledge of linear algebra and real analysis. Topics covered include: Mathematical programming: Markov decision processes (the non-competitive case), and stochastic games via mathematical programming.- Existence, structure and applications: Summable stochastic games, average-reward stochastic games and applications and special classes of stochastic games.- Appendices on: matrix games, bimatrix games and nonlinear programming; a theorem of Hardy and Littlewood; Markov chains; and complex varieties and the limit discount equation.
We are committed to protecting your rights under the Consumer Guarantees Act and working with our suppliers to assist with warranty claims. Products sold by Mighty Ape will be covered by a Manufacturer's Warranty for at least a one-year period from the date of purchase.
Your warranty will cover any manufacturing defects which, if existing, will present themselves within this warranty period.
Your warranty will not cover normal wear and tear, faults caused by misuse, and accidents which cause damage or theft caused after delivery. Using the product in a way it is not designed for will void your warranty.
Please refer to our Help Centre for more information.