Vor Ort
Merkzettel Warenkorb
Produktbild: Approximate Dynamic Programmin

Approximate Dynamic Programmin

Aus der Reihe Wiley Series in Probability and Statistics

169,99 €

inkl. gesetzl. MwSt., Versandkostenfrei

Produktdetails

Einband

Gebundene Ausgabe

Erscheinungsdatum

22.09.2011

Verlag

John Wiley & Sons

Seitenzahl

656

Maße (L/B/H)

24/16,1/4 cm

Gewicht

1144 g

Auflage

2nd edition

Sprache

Englisch

ISBN

978-0-470-60445-8

Produktdetails

Einband

Gebundene Ausgabe

Erscheinungsdatum

22.09.2011

Verlag

John Wiley & Sons

Seitenzahl

656

Maße (L/B/H)

24/16,1/4 cm

Gewicht

1144 g

Auflage

2nd edition

Sprache

Englisch

ISBN

978-0-470-60445-8

Herstelleradresse

Libri GmbH
Europaallee 1
36244 Bad Hersfeld
DE

Email: gpsr@libri.de

Noch keine Bewertungen vorhanden

Verfassen Sie die erste Bewertung zu diesem Artikel

Helfen Sie anderen Kundinnen und Kunden durch Ihre Meinung.

Kundinnen und Kunden meinen

Bewertungen (0)
Die Leseprobe wird geladen.
  • Produktbild: Approximate Dynamic Programmin
  • Preface to the Second Edition xi
     
    Preface to the First Edition xv
     
    Acknowledgments xvii
     
    1 The Challenges of Dynamic Programming 1
     
    1.1 A Dynamic Programming Example: A Shortest Path Problem, 2
     
    1.2 The Three Curses of Dimensionality, 3
     
    1.3 Some Real Applications, 6
     
    1.4 Problem Classes, 11
     
    1.5 The Many Dialects of Dynamic Programming, 15
     
    1.6 What Is New in This Book?, 17
     
    1.7 Pedagogy, 19
     
    1.8 Bibliographic Notes, 22
     
    2 Some Illustrative Models 25
     
    2.1 Deterministic Problems, 26
     
    2.2 Stochastic Problems, 31
     
    2.3 Information Acquisition Problems, 47
     
    2.4 A Simple Modeling Framework for Dynamic Programs, 50
     
    2.5 Bibliographic Notes, 54
     
    Problems, 54
     
    3 Introduction to Markov Decision Processes 57
     
    3.1 The Optimality Equations, 58
     
    3.2 Finite Horizon Problems, 65
     
    3.3 Infinite Horizon Problems, 66
     
    3.4 Value Iteration, 68
     
    3.5 Policy Iteration, 74
     
    3.6 Hybrid Value-Policy Iteration, 75
     
    3.7 Average Reward Dynamic Programming, 76
     
    3.8 The Linear Programming Method for Dynamic Programs, 77
     
    3.9 Monotone Policies*, 78
     
    3.10 Why Does It Work?**, 84
     
    3.11 Bibliographic Notes, 103
     
    Problems, 103
     
    4 Introduction to Approximate Dynamic Programming 111
     
    4.1 The Three Curses of Dimensionality (Revisited), 112
     
    4.2 The Basic Idea, 114
     
    4.3 Q-Learning and SARSA, 122
     
    4.4 Real-Time Dynamic Programming, 126
     
    4.5 Approximate Value Iteration, 127
     
    4.6 The Post-Decision State Variable, 129
     
    4.7 Low-Dimensional Representations of Value Functions, 144
     
    4.8 So Just What Is Approximate Dynamic Programming?, 146
     
    4.9 Experimental Issues, 149
     
    4.10 But Does It Work?, 155
     
    4.11 Bibliographic Notes, 156
     
    Problems, 158
     
    5 Modeling Dynamic Programs 167
     
    5.1 Notational Style, 169
     
    5.2 Modeling Time, 170
     
    5.3 Modeling Resources, 174
     
    5.4 The States of Our System, 178
     
    5.5 Modeling Decisions, 187
     
    5.6 The Exogenous Information Process, 189
     
    5.7 The Transition Function, 198
     
    5.8 The Objective Function, 206
     
    5.9 A Measure-Theoretic View of Information**, 211
     
    5.10 Bibliographic Notes, 213
     
    Problems, 214
     
    6 Policies 221
     
    6.1 Myopic Policies, 224
     
    6.2 Lookahead Policies, 224
     
    6.3 Policy Function Approximations, 232
     
    6.4 Value Function Approximations, 235
     
    6.5 Hybrid Strategies, 239
     
    6.6 Randomized Policies, 242
     
    6.7 How to Choose a Policy?, 244
     
    6.8 Bibliographic Notes, 247
     
    Problems, 247
     
    7 Policy Search 249
     
    7.1 Background, 250
     
    7.2 Gradient Search, 253
     
    7.3 Direct Policy Search for Finite Alternatives, 256
     
    7.4 The Knowledge Gradient Algorithm for Discrete Alternatives, 262
     
    7.5 Simulation Optimization, 270
     
    7.6 Why Does It Work?**, 274
     
    7.7 Bibliographic Notes, 285
     
    Problems, 286
     
    8 Approximating Value Functions 289
     
    8.1 Lookup Tables and Aggregation, 290
     
    8.2 Parametric Models, 304
     
    8.3 Regression Variations, 314
     
    8.4 Nonparametric Models, 316
     
    8.5 Approximations and the Curse of Dimensionality, 325
     
    8.6 Why Does It Work?**, 328
     
    8.7 Bibliographic Notes, 333
     
    Problems, 334
     
    9 Learning Value Function Approximations 337
     
    9.1 Sampling the Value