An Algorithmic Perspective on Imitation Learning
Seiten
2018
now publishers Inc (Verlag)
978-1-68083-410-9 (ISBN)
now publishers Inc (Verlag)
978-1-68083-410-9 (ISBN)
Familiarizes machine learning experts with imitation learning, statistical supervised learning theory, and reinforcement learning and roboticists and experts in applied AI with broader appreciation for the frameworks and tools available for imitation learning.
As robots and other intelligent agents move from simple environments and problems to more complex, unstructured settings, manually programming their behavior has become increasingly challenging and expensive. Often, it is easier for a teacher to demonstrate a desired behavior rather than attempt to manually engineer it. This process of learning from demonstrations, and the study of algorithms to do so, is called imitation learning. An Algorithmic Perspective on Imitation Learning provides the reader with an introduction to imitation learning. It covers the underlying assumptions, approaches, and how they relate; the rich set of algorithms developed to tackle the problem; and advice on effective tools and implementation. An Algorithmic Perspective on Imitation Learning serves two audiences. First, it familiarizes machine learning experts with the challenges of imitation learning, particularly those arising in robotics, and the interesting theoretical and practical distinctions between it and more familiar frameworks like statistical supervised learning theory and reinforcement learning. Second, it provides roboticists and experts in applied artificial intelligence with a broader appreciation for the frameworks and tools available for imitation learning. It pays particular attention to the intimate connection between imitation learning approaches and those of structured prediction.
As robots and other intelligent agents move from simple environments and problems to more complex, unstructured settings, manually programming their behavior has become increasingly challenging and expensive. Often, it is easier for a teacher to demonstrate a desired behavior rather than attempt to manually engineer it. This process of learning from demonstrations, and the study of algorithms to do so, is called imitation learning. An Algorithmic Perspective on Imitation Learning provides the reader with an introduction to imitation learning. It covers the underlying assumptions, approaches, and how they relate; the rich set of algorithms developed to tackle the problem; and advice on effective tools and implementation. An Algorithmic Perspective on Imitation Learning serves two audiences. First, it familiarizes machine learning experts with the challenges of imitation learning, particularly those arising in robotics, and the interesting theoretical and practical distinctions between it and more familiar frameworks like statistical supervised learning theory and reinforcement learning. Second, it provides roboticists and experts in applied artificial intelligence with a broader appreciation for the frameworks and tools available for imitation learning. It pays particular attention to the intimate connection between imitation learning approaches and those of structured prediction.
1. Introduction 2. Design of Imitation Learning Algorithms 3. Behavioral Cloning 4. Inverse Reinforcement Learning 5. Challenges in Imitation Learning for Robotics. Acknowledgements. References.
Erscheinungsdatum | 11.04.2018 |
---|---|
Reihe/Serie | Foundations and Trends in Robotics |
Verlagsort | Hanover |
Sprache | englisch |
Themenwelt | Technik ► Elektrotechnik / Energietechnik |
Technik ► Maschinenbau | |
ISBN-10 | 1-68083-410-X / 168083410X |
ISBN-13 | 978-1-68083-410-9 / 9781680834109 |
Zustand | Neuware |
Haben Sie eine Frage zum Produkt? |
Mehr entdecken
aus dem Bereich
aus dem Bereich
DIN-Normen und Technische Regeln für die Elektroinstallation
Buch | Softcover (2023)
Beuth (Verlag)
86,00 €
Kolbenmaschinen - Strömungsmaschinen - Kraftwerke
Buch | Hardcover (2023)
Hanser (Verlag)
49,99 €