EUR 33,34
Quantité disponible : 1 disponible(s)
Ajouter au panierPAP. Etat : New. New Book. Shipped from UK. Established seller since 2000.
EUR 31,25
Quantité disponible : 1 disponible(s)
Ajouter au panierPAP. Etat : New. New Book. Shipped from UK. Established seller since 2000.
Langue: anglais
Edité par Springer International Publishing AG, CH, 2017
ISBN 10 : 3031004485 ISBN 13 : 9783031004483
Vendeur : Rarewaves.com USA, London, LONDO, Royaume-Uni
EUR 39,89
Quantité disponible : 1 disponible(s)
Ajouter au panierPaperback. Etat : New. 1°. Many real-world decision problems have multiple objectives. For example, when choosing a medical treatment plan, we want to maximize the efficacy of the treatment, but also minimize the side effects. These objectives typically conflict, e.g., we can often increase the efficacy of the treatment, but at the cost of more severe side effects. In this book, we outline how to deal with multiple objectives in decision-theoretic planning and reinforcement learning algorithms. To illustrate this, we employ the popular problem classes of multi-objective Markov decision processes (MOMDPs) and multi-objective coordination graphs (MO-CoGs).First, we discuss different use cases for multi-objective decision making, and why they often necessitate explicitly multi-objective algorithms. We advocate a utility-based approach to multi-objective decision making, i.e., that what constitutes an optimal solution to a multi-objective decision problem should be derived from the availableinformation about user utility. We show how different assumptions about user utility and what types of policies are allowed lead to different solution concepts, which we outline in a taxonomy of multi-objective decision problems.Second, we show how to create new methods for multi-objective decision making using existing single-objective methods as a basis. Focusing on planning, we describe two ways to creating multi-objective algorithms: in the inner loop approach, the inner workings of a single-objective method are adapted to work with multi-objective solution concepts; in the outer loop approach, a wrapper is created around a single-objective method that solves the multi-objective problem as a series of single-objective problems. After discussing the creation of such methods for the planning setting, we discuss how these approaches apply to the learning setting.Next, we discuss three promising application domains for multi-objective decision making algorithms: energy, health, and infrastructure and transportation. Finally, we conclude by outlining important open problems and promising future directions.
Vendeur : Lucky's Textbooks, Dallas, TX, Etats-Unis
EUR 36,59
Quantité disponible : Plus de 20 disponibles
Ajouter au panierEtat : New.
Vendeur : California Books, Miami, FL, Etats-Unis
EUR 42,25
Quantité disponible : Plus de 20 disponibles
Ajouter au panierEtat : New.
Vendeur : Ria Christie Collections, Uxbridge, Royaume-Uni
EUR 33,94
Quantité disponible : 1 disponible(s)
Ajouter au panierEtat : New. In English.
Vendeur : Books Puddle, New York, NY, Etats-Unis
EUR 46,78
Quantité disponible : 4 disponible(s)
Ajouter au panierEtat : New. 1st edition NO-PA16APR2015-KAP.
EUR 34,99
Quantité disponible : 10 disponible(s)
Ajouter au panierPF. Etat : New.
EUR 28,46
Quantité disponible : 1 disponible(s)
Ajouter au panierEtat : NEW.
EUR 75,13
Quantité disponible : 1 disponible(s)
Ajouter au panierPaperback. Etat : Brand New. 129 pages. 9.50x7.50x0.25 inches. In Stock.
Langue: anglais
Edité par Springer, Berlin|Springer International Publishing|Morgan & Claypool|Springer, 2017
ISBN 10 : 3031004485 ISBN 13 : 9783031004483
Vendeur : moluna, Greven, Allemagne
EUR 37,61
Quantité disponible : 1 disponible(s)
Ajouter au panierEtat : New. Many real-world decision problems have multiple objectives. For example, when choosing a medical treatment plan, we want to maximize the efficacy of the treatment, but also minimize the side effects. These objectives typically conflict, e.g., we can ofte.
Langue: anglais
Edité par Springer International Publishing AG, CH, 2017
ISBN 10 : 3031004485 ISBN 13 : 9783031004483
Vendeur : Rarewaves.com UK, London, Royaume-Uni
EUR 36,76
Quantité disponible : 1 disponible(s)
Ajouter au panierPaperback. Etat : New. 1°. Many real-world decision problems have multiple objectives. For example, when choosing a medical treatment plan, we want to maximize the efficacy of the treatment, but also minimize the side effects. These objectives typically conflict, e.g., we can often increase the efficacy of the treatment, but at the cost of more severe side effects. In this book, we outline how to deal with multiple objectives in decision-theoretic planning and reinforcement learning algorithms. To illustrate this, we employ the popular problem classes of multi-objective Markov decision processes (MOMDPs) and multi-objective coordination graphs (MO-CoGs).First, we discuss different use cases for multi-objective decision making, and why they often necessitate explicitly multi-objective algorithms. We advocate a utility-based approach to multi-objective decision making, i.e., that what constitutes an optimal solution to a multi-objective decision problem should be derived from the availableinformation about user utility. We show how different assumptions about user utility and what types of policies are allowed lead to different solution concepts, which we outline in a taxonomy of multi-objective decision problems.Second, we show how to create new methods for multi-objective decision making using existing single-objective methods as a basis. Focusing on planning, we describe two ways to creating multi-objective algorithms: in the inner loop approach, the inner workings of a single-objective method are adapted to work with multi-objective solution concepts; in the outer loop approach, a wrapper is created around a single-objective method that solves the multi-objective problem as a series of single-objective problems. After discussing the creation of such methods for the planning setting, we discuss how these approaches apply to the learning setting.Next, we discuss three promising application domains for multi-objective decision making algorithms: energy, health, and infrastructure and transportation. Finally, we conclude by outlining important open problems and promising future directions.
Vendeur : Revaluation Books, Exeter, Royaume-Uni
EUR 36,45
Quantité disponible : 1 disponible(s)
Ajouter au panierPaperback. Etat : Brand New. 128 pages. 9.25x7.51x9.25 inches. In Stock. This item is printed on demand.
Vendeur : Majestic Books, Hounslow, Royaume-Uni
EUR 47,02
Quantité disponible : 4 disponible(s)
Ajouter au panierEtat : New. Print on Demand.
Vendeur : Biblios, Frankfurt am main, HESSE, Allemagne
EUR 48,77
Quantité disponible : 4 disponible(s)
Ajouter au panierEtat : New. PRINT ON DEMAND.