Explainable and Interpretable Reinforcement Learning for Robotics
-
- Hardcover
- Taschenbuch ausgewählt
- eBook
-
Sprache:Englisch
54,99 €
inkl. gesetzl. MwSt.,
Beschreibung
Produktdetails
Einband
Taschenbuch
Erscheinungsdatum
20.03.2025
Abbildungen
XV, 114 p. 14 illus., 13 illus. in color.
Verlag
SpringerSeitenzahl
114
Maße (L/B/H)
24/16,8/0,8 cm
Gewicht
236 g
Sprache
Englisch
ISBN
978-3-031-47520-7
This book surveys the state of the art in explainable and interpretable reinforcement learning (RL) as relevant for robotics. While RL in general has grown in popularity and been applied to increasingly complex problems, several challenges have impeded the real-world adoption of RL algorithms for robotics and related areas. These include difficulties in preventing safety constraints from being violated and the issues faced by systems operators who desire explainable policies and actions. Robotics applications present a unique set of considerations and result in a number of opportunities related to their physical, real-world sensory input and interactions.
The authors consider classification techniques used in past surveys and papers and attempt to unify terminology across the field. The book provides an in-depth exploration of 12 attributes that can be used to classify explainable/interpretable techniques. These include whether the RL method is model-agnostic or model-specific, self-explainable or post-hoc, as well as additional analysis of the attributes of scope, when-produced, format, knowledge limits, explanation accuracy, audience, predictability, legibility, readability, and reactivity. The book is organized around a discussion of these methods broken down into 42 categories and subcategories, where each category can be classified according to some of the attributes. The authors close by identifying gaps in the current research and highlighting areas for future investigation.Noch keine Bewertungen vorhanden
Verfassen Sie die erste Bewertung zu diesem Artikel
Helfen Sie anderen Kundinnen und Kunden durch Ihre Meinung.
Kurze Frage zu unserer Seite
Vielen Dank für dein Feedback
Wir nutzen dein Feedback, um unsere Produktseiten zu verbessern. Bitte habe Verständnis, dass wir dir keine Rückmeldung geben können. Falls du Kontakt mit uns aufnehmen möchtest, kannst du dich aber gerne an unseren Kund*innenservice wenden.
zum Kundenservice