Explainable and Interpretable Reinforcement Learning for Robotics
Series: Synthesis Lectures on Artificial Intelligence and Machine Learning;
- Publisher's listprice EUR 58.84
-
24 403 Ft (23 241 Ft + 5% VAT)
The price is estimated because at the time of ordering we do not know what conversion rates will apply to HUF / product currency when the book arrives. In case HUF is weaker, the price increases slightly, in case HUF is stronger, the price goes lower slightly.
- Discount 20% (cc. 4 881 Ft off)
- Discounted price 19 522 Ft (18 593 Ft + 5% VAT)
Subcribe now and take benefit of a favourable price.
Subscribe
24 403 Ft
Availability
printed on demand
Why don't you give exact delivery time?
Delivery time is estimated on our previous experiences. We give estimations only, because we order from outside Hungary, and the delivery time mainly depends on how quickly the publisher supplies the book. Faster or slower deliveries both happen, but we do our best to supply as quickly as possible.
Product details:
- Publisher Springer International Publishing
- Date of Publication 20 March 2025
- Number of Volumes 1 pieces, Book
- ISBN 9783031475207
- Binding Paperback
- See also 9783031475177
- No. of pages114 pages
- Size 240x168 mm
- Language English
- Illustrations XV, 114 p. 14 illus., 13 illus. in color. Illustrations, black & white 647
Categories
Long description:
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.Table of Contents:
Introduction.- Classification System.- Explainable Methods Organized by Category.- 4 Key Considerations and Resources.- Opportunities, Challenges, and Future Directions.
More
Integrated Process Design and Operational Optimization Via Multiparametric Programming
36 083 HUF
33 197 HUF
