000 04404nam a22005295i 4500
001 978-3-031-01576-2
003 DE-He213
005 20240730163428.0
007 cr nn 008mamaa
008 220601s2017 sz | s |||| 0|eng d
020 _a9783031015762
_9978-3-031-01576-2
024 7 _a10.1007/978-3-031-01576-2
_2doi
050 4 _aQ334-342
050 4 _aTA347.A78
072 7 _aUYQ
_2bicssc
072 7 _aCOM004000
_2bisacsh
072 7 _aUYQ
_2thema
082 0 4 _a006.3
_223
100 1 _aRoijers, Diederik M.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_978463
245 1 0 _aMulti-Objective Decision Making
_h[electronic resource] /
_cby Diederik M. Roijers, Shimon Whiteson.
250 _a1st ed. 2017.
264 1 _aCham :
_bSpringer International Publishing :
_bImprint: Springer,
_c2017.
300 _aXVII, 111 p.
_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 _aPreface -- Acknowledgments -- Table of Abbreviations -- Introduction -- Multi-Objective Decision Problems -- Taxonomy -- Inner Loop Planning -- Outer Loop Planning -- Learning -- Applications -- Conclusions and Future Work -- Bibliography -- Authors' Biographies .
520 _aMany real-world decision problems have multiple objectives. For example, when choosing a medical treatment plan, we want to maximize the efficacy of the treatment, but also minimize the side effects. These objectives typically conflict, e.g., we can often increase the efficacy of the treatment, but at the cost of more severe side effects. In this book, we outline how to deal with multiple objectives in decision-theoretic planning and reinforcement learning algorithms. To illustrate this, we employ the popular problem classes of multi-objective Markov decision processes (MOMDPs) and multi-objective coordination graphs (MO-CoGs). First, we discuss different use cases for multi-objective decision making, and why they often necessitate explicitly multi-objective algorithms. We advocate a utility-based approach to multi-objective decision making, i.e., that what constitutes an optimal solution to a multi-objective decision problem should be derived from the availableinformation about user utility. We show how different assumptions about user utility and what types of policies are allowed lead to different solution concepts, which we outline in a taxonomy of multi-objective decision problems. Second, we show how to create new methods for multi-objective decision making using existing single-objective methods as a basis. Focusing on planning, we describe two ways to creating multi-objective algorithms: in the inner loop approach, the inner workings of a single-objective method are adapted to work with multi-objective solution concepts; in the outer loop approach, a wrapper is created around a single-objective method that solves the multi-objective problem as a series of single-objective problems. After discussing the creation of such methods for the planning setting, we discuss how these approaches apply to the learning setting. Next, we discuss three promising application domains for multi-objective decision making algorithms: energy, health, and infrastructure and transportation. Finally, we conclude by outlining important open problems and promising future directions.
650 0 _aArtificial intelligence.
_93407
650 0 _aMachine learning.
_91831
650 0 _aNeural networks (Computer science) .
_978464
650 1 4 _aArtificial Intelligence.
_93407
650 2 4 _aMachine Learning.
_91831
650 2 4 _aMathematical Models of Cognitive Processes and Neural Networks.
_932913
700 1 _aWhiteson, Shimon.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_978465
710 2 _aSpringerLink (Online service)
_978466
773 0 _tSpringer Nature eBook
776 0 8 _iPrinted edition:
_z9783031004483
776 0 8 _iPrinted edition:
_z9783031027048
830 0 _aSynthesis Lectures on Artificial Intelligence and Machine Learning,
_x1939-4616
_978467
856 4 0 _uhttps://doi.org/10.1007/978-3-031-01576-2
912 _aZDB-2-SXSC
942 _cEBK
999 _c84595
_d84595