Найти книгу: "Markov Decision Processes in Artificial Intelligence"

Markov Decision Processes (MDPs) are a mathematical framework for modeling sequential decision problems under uncertainty as well as Reinforcement Learning problems. Written by experts in the field, this book provides a global view of current research using MDPs in Artificial Intelligence. It starts with an introductory presentation of the fundamental aspects of MDPs (planning in MDPs, Reinforcement Learning, Partially Observable MDPs, Markov games and the use of non-classical criteria). Then it presents more advanced research trends in the domain and gives some concrete examples using illustrative applications.

Учебное пособие предназначено для обучения магистров по направлению «Химическая технология» и его содержание соответствует ФГОС 3-го поколения для дисциплины «Процессы массопереноса в системах с участием твердой фазы». Изложенный в учебном пособии материал позволяет студентам восполнить и систематизировать знания по теории массообменных процессов, знакомит со спецификой массопереноса в системах с участием твердой фазы, а также с такими процессами, как адсорбция, ионный обмен, кристаллизация, растворение, мембранное разделение, конструкциями соответствующих аппаратов и методами их расчетов.

Decision making by the aircrafts services of the international airport, which provides for intensive traffic of aircraft and their ground handling, becomes a very topical issue. If earlier it was believed that the intensity is provided only by the number of runways, nowadays a large accumulation of aircraft on the airport platform-field creates equally complex difficulties in comparison with aircraft take-offs and landings. Solving such problems with the use of «crisp methods» of queuing theory gives little. This article deals with modern «fuzzy methods» based on simulation modeling and fuzzy logic.

The training system is implemented with the use of the fuzzy classifier that represents fuzzy knowledge base, the input of which receives signals about current state of the traction rolling stock and of the environment. The results of the work allow implementing intelligent DSS in modern locomotives. This will enhance the level of safety and efficiency of driving a train.