Welcome to P K Kelkar Library, Online Public Access Catalogue (OPAC)

Explainable and interpretable reinforcement learning for robotics (Record no. 567636)

MARC details
000 -LEADER
fixed length control field 02582 a2200265 4500
003 - CONTROL NUMBER IDENTIFIER
control field OSt
005 - DATE AND TIME OF LATEST TRANSACTION
control field 20250910154708.0
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 250910b |||||||| |||| 00| 0 eng d
020 ## - INTERNATIONAL STANDARD BOOK NUMBER
ISBN 9783031475177
082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER
Classification number 006.3223
Item number Ex73e
245 ## - TITLE STATEMENT
Title Explainable and interpretable reinforcement learning for robotics
Statement of responsibility, etc Aaron M Roth...[et al.]
260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT)
Name of publisher Springer
Year of publication 2024
Place of publication Switzerland
300 ## - PHYSICAL DESCRIPTION
Number of Pages xi, 113p
440 ## - SERIES STATEMENT/ADDED ENTRY--TITLE
Title Synthesis lectures on artificial intelligence and machine learning
490 ## - SERIES STATEMENT
Series statement / edited by Ron Brachman
520 ## - SUMMARY, ETC.
Summary, etc 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. In addition, this book: Provides readers with a categorization system to discuss explainable and interpretable RL techniques Explores RL methodology specific to robotics applications Explains how interpretable RL algorithms can enhance trust, increase adoption, reduce risk, and increase safety.
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical Term Machine learning
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical Term Robotics
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical Term Automatic control
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical Term Artificial Intelligence
700 ## - ADDED ENTRY--PERSONAL NAME
Personal name Manocha, Dinesh
700 ## - ADDED ENTRY--PERSONAL NAME
Personal name Sriram, Ram D
700 ## - ADDED ENTRY--PERSONAL NAME
Personal name Tabassi, Elham
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Koha item type Books
Holdings
Withdrawn status Lost status Damaged status Not for loan Collection code Home library Current library Date acquired Source of acquisition Cost, normal purchase price Full call number Accession Number Cost, replacement price Koha item type
        In Acquisition PK Kelkar Library, IIT Kanpur PK Kelkar Library, IIT Kanpur 10/09/2025 2 4207.97 006.3223 Ex73e A187032 5610.63 Reference

Powered by Koha