Foundations of deep reinforcement learning : theory and practice in Python
Bibliographische Detailangaben
- Titel
- Foundations of deep reinforcement learning theory and practice in Python
- verantwortlich
- ;
- veröffentlicht
- Erscheinungsjahr
- 2020
- Teil von
- Addison-Wesley data and analytics series.
- Medientyp
- Buch
- Datenquelle
- British Library Catalogue
- Tags
- Tag hinzufügen
Zugang
Weitere Informationen sehen Sie, wenn Sie angemeldet sind. Noch keinen Account? Jetzt registrieren.
- Details Klicken Sie hier, um den Inhalt der Registerkarte zu laden.
- Standorte Klicken Sie hier, um den Inhalt der Registerkarte zu laden.
- Internformat Klicken Sie hier, um den Inhalt der Registerkarte zu laden.
- Zusammenfassung
- "Foundations of Deep Reinforcement Learning is the fastest, most accessible introduction to deep reinforcement learning (DRL). Deep reinforcement learning (DRL) systems are achieving breakthrough performance in many applications. DRL machine learning resembles human learning in multiple ways: It's exceptionally flexible, can learn and discover strategies without supervision, and can efficiently balance exploration with exploitation. The authors begin with intuition, then carefully explain DRL theory and algorithms, and finish with implementations and practical tips. Throughout, the authors bridge theory and practice, helping you integrate components and tune parameters that must work together optimally for DRL algorithms to succeed. They illuminate important recent advances through hands-on examples written in Python and built with their advanced SLM Lab software library. This guide is intended for both computer science students and software engineers who are familiar with basic machine learning concepts and have a working understanding of Python"--
- Umfang
- xxiv, 379 pages; illustrations; 24 cm
- Sprache
- Englisch
- Schlagworte
- DDC-Notation
- 006.31
- Bibliografie
- Includes bibliographical references and index.
- ISBN
-
0135172381
9780135172384