000 04552nam a22006375i 4500
001 978-3-031-47518-4
003 DE-He213
005 20251030111728.0
007 cr nn 008mamaa
008 240319s2024 sz | s |||| 0|eng d
020 _a9783031475184
_9978-3-031-47518-4
024 7 _a10.1007/978-3-031-47518-4
_2doi
050 4 _aQ334-342
050 4 _aTA347.A78
072 7 _aUYQ
_2bicssc
072 7 _aCOM004000
_2bisacsh
072 7 _aUYQ
_2thema
100 1 _aRoth, Aaron M.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_973298
245 1 0 _aExplainable and Interpretable Reinforcement Learning for Robotics
_h[electronic resource] /
_cby Aaron M. Roth, Dinesh Manocha, Ram D. Sriram, Elham Tabassi.
250 _a1st ed. 2024.
264 1 _aCham :
_bSpringer International Publishing :
_bImprint: Springer,
_c2024.
300 _aXV, 114 p. 14 illus., 13 illus. in color.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aSynthesis Lectures on Artificial Intelligence and Machine Learning,
_x1939-4616
505 0 _aIntroduction -- Classification System -- Explainable Methods Organized by Category -- 4 Key Considerations and Resources -- Opportunities, Challenges, and Future Directions.
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 0 _aArtificial intelligence.
_958441
650 0 _aMachine learning.
_955059
650 0 _aRobotics.
_959148
650 0 _aControl engineering.
650 0 _aAutomation.
_959149
650 0 _aInformation visualization.
_964751
650 1 4 _aArtificial Intelligence.
_958441
650 2 4 _aMachine Learning.
_955059
650 2 4 _aRobotics.
_959148
650 2 4 _aRobotic Engineering.
_966064
650 2 4 _aControl, Robotics, Automation.
650 2 4 _aData and Information Visualization.
_966435
700 1 _aManocha, Dinesh.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_973299
700 1 _aSriram, Ram D.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_973300
700 1 _aTabassi, Elham.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_973301
710 2 _aSpringerLink (Online service)
773 0 _tSpringer Nature eBook
776 0 8 _iPrinted edition:
_z9783031475177
776 0 8 _iPrinted edition:
_z9783031475191
776 0 8 _iPrinted edition:
_z9783031475207
830 0 _aSynthesis Lectures on Artificial Intelligence and Machine Learning,
_x1939-4616
_973302
856 4 0 _uhttps://doi.org/10.1007/978-3-031-47518-4
912 _aZDB-2-SXSC
999 _c58430
_d58430