000			02582 a2200265 4500
003			OSt
005			20250910154708.0
008			250910b |||||||| |||| 00| 0 eng d
020			_a9783031475177
082			_a006.3223 _bEx73e
245			_aExplainable and interpretable reinforcement learning for robotics _cAaron M Roth...[et al.]
260			_bSpringer _c2024 _aSwitzerland
300			_axi, 113p
440			_aSynthesis lectures on artificial intelligence and machine learning
490			_a/ edited by Ron Brachman
520			_aThis 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			_aMachine learning
650			_aRobotics
650			_aAutomatic control
650			_aArtificial Intelligence
700			_aManocha, Dinesh
700			_aSriram, Ram D
700			_aTabassi, Elham
942			_cBK
999			_c567636 _d567636