04552nam a22006375i 4500 978-3-031-47518-4 DE-He213 20251030111728.0 cr nn 008mamaa 240319s2024 sz | s |||| 0|eng d 9783031475184 978-3-031-47518-4 10.1007/978-3-031-47518-4 doi Q334-342 TA347.A78 UYQ bicssc COM004000 bisacsh UYQ thema Roth, Aaron M. author. aut http://id.loc.gov/vocabulary/relators/aut 73298 Explainable and Interpretable Reinforcement Learning for Robotics [electronic resource] / by Aaron M. Roth, Dinesh Manocha, Ram D. Sriram, Elham Tabassi. 1st ed. 2024. Cham : Springer International Publishing : Imprint: Springer, 2024. XV, 114 p. 14 illus., 13 illus. in color. online resource. text txt rdacontent computer c rdamedia online resource cr rdacarrier text file PDF rda Synthesis Lectures on Artificial Intelligence and Machine Learning, 1939-4616 Introduction -- Classification System -- Explainable Methods Organized by Category -- 4 Key Considerations and Resources -- Opportunities, Challenges, and Future Directions. 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. Artificial intelligence. 58441 Machine learning. 55059 Robotics. 59148 Control engineering. Automation. 59149 Information visualization. 64751 Artificial Intelligence. 58441 Machine Learning. 55059 Robotics. 59148 Robotic Engineering. 66064 Control, Robotics, Automation. Data and Information Visualization. 66435 Manocha, Dinesh. author. aut http://id.loc.gov/vocabulary/relators/aut 73299 Sriram, Ram D. author. aut http://id.loc.gov/vocabulary/relators/aut 73300 Tabassi, Elham. author. aut http://id.loc.gov/vocabulary/relators/aut 73301 SpringerLink (Online service) Springer Nature eBook Printed edition: 9783031475177 Printed edition: 9783031475191 Printed edition: 9783031475207 Synthesis Lectures on Artificial Intelligence and Machine Learning, 1939-4616 73302 https://doi.org/10.1007/978-3-031-47518-4 ZDB-2-SXSC 58430 58430