Hugendubel.info - Die B2B Online-Buchhandlung 

Merkliste
Die Merkliste ist leer.
Bitte warten - die Druckansicht der Seite wird vorbereitet.
Der Druckdialog öffnet sich, sobald die Seite vollständig geladen wurde.
Sollte die Druckvorschau unvollständig sein, bitte schliessen und "Erneut drucken" wählen.

From Shortest Paths to Reinforcement Learning

A MATLAB-Based Tutorial on Dynamic Programming
BuchKartoniert, Paperback
207 Seiten
Englisch
Springererschienen am12.01.20221st ed. 2021
Dynamic programming (DP) has a relevant history as a powerful and flexible optimization principle, but has a bad reputation as a computationally impractical tool.mehr
Verfügbare Formate
BuchGebunden
EUR106,99
BuchKartoniert, Paperback
EUR69,54
E-BookPDF1 - PDF WatermarkE-Book
EUR69,54

Produkt

KlappentextDynamic programming (DP) has a relevant history as a powerful and flexible optimization principle, but has a bad reputation as a computationally impractical tool.
Zusammenfassung
Covers both, classical numerical analysis approaches and more recent learning strategies based on Monte Carlo simulation

Includes well-documented MATLAB code snapshots to illustrate algorithms and applications in detail

Illustrate subtle modeling issues in detail

Illustrates a wide set of applications

Includes supplementary material: sn.pub/extras
Details
ISBN/GTIN978-3-030-61869-8
ProduktartBuch
EinbandartKartoniert, Paperback
Verlag
Erscheinungsjahr2022
Erscheinungsdatum12.01.2022
Auflage1st ed. 2021
ReiheEURO Advanced Tutorials on Operational Research
Seiten207 Seiten
SpracheEnglisch
IllustrationenXI, 207 p. 67 illus.
Artikel-Nr.50393376
Rubriken
GenreWirtschaft

Inhalt/Kritik

Inhaltsverzeichnis
The dynamic programming principle.- Implementing dynamic programming.- Modeling for dynamic programming.- Numerical dynamic programming for discrete states.- Approximate dynamic programming and reinforcement learning for discrete states.- Numerical dynamic programming for continuous states.- Approximate dynamic programming and reinforcement learning for continuous states.mehr

Schlagworte

Autor

Paolo Brandimarte is full professor at the Department of Mathematical Sciences of Politecnico di Torino, Italy, where he teaches courses on Business Analytics, Risk Management, and Operations Research. He is the author of more than ten books on the application of optimization and simulation methods to problems ranging from quantitative finance to production and supply chain management.